PraisonAI
by PraisonAI
CVEs (35)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-57132 | hig | 0.45 | — | — | Jun 18, 2026 | ### Summary Setting `PRAISONAI_CALL_AUTH=disabled` completely disables all authentication on the `/api/v1/agents/{id}/invoke` endpoint. This bypass is advertised in the application's own error messages, making it likely to appear in production Docker and Compose configurations. … | ||
| CVE-2026-57143 | hig | 0.45 | — | — | Jun 18, 2026 | ### Summary A Server-Side Request Forgery (SSRF) vulnerability in the SearxNG / `search_web` search tools allows an attacker to make the server perform requests to arbitrary internal endpoints and read the responses back. The `searxng_url` argument is passed directly to… | ||
| CVE-2026-57113 | hig | 0.45 | — | — | Jun 18, 2026 | ## Summary PraisonAI's template loader accepts GitHub template URIs with refs, for example `github:owner/repo/[email protected]`. The resolver stores the user-controlled template path and ref verbatim, and the cache layer later joins those values into… | ||
| CVE-2026-57119 | hig | 0.45 | — | — | Jun 18, 2026 | ### Summary An unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the `agent_file` field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. ### Details The… | ||
| CVE-2026-56838 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI `recipe.run_stream()` skips dangerous-tool policy enforcement ## Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes `allow_dangerous_tools=True`. The normal `recipe.run()` path enforces this with… | ||
| CVE-2026-56840 | hig | 0.45 | — | — | Jun 18, 2026 | # HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools ## Summary `praisonai.bots.HTTPApproval` renders pending tool approval arguments directly into the approval dashboard HTML. An attacker-controlled tool argument… | ||
| CVE-2026-56837 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI LinearBot processes unsigned webhooks when `LINEAR_WEBHOOK_SECRET` is missing ## Summary PraisonAI's LinearBot starts a public webhook listener on `0.0.0.0` and treats `LINEAR_WEBHOOK_SECRET` as optional. When the secret is absent, startup only logs a warning and… | ||
| CVE-2026-56834 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage ## Summary PraisonAI's Dynamic Context Discovery feature exposes artifact helper tools through `ctx.get_tools()`: ```python ctx = setup_dynamic_context() agent = Agent( … | ||
| CVE-2026-56835 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI Slack `app_mention` bypasses configured user/channel authorization ## Summary PraisonAI's Slack bot applies its configured `allowed_users`, `allowed_channels`, and unknown-user pairing policy in the normal Slack `message` event handler, but not in the adjacent… | ||
| CVE-2026-56836 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI `recipe serve` Typer command bypasses the non-localhost authentication guard ## Summary PraisonAI's installed console entrypoint is Typer-first. In current releases, the `recipe` command is registered in the Typer app and `praisonai recipe serve` dispatches to the… | ||
| CVE-2026-57112 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools ## Summary `praisonaiagents.mcp.ToolsMCPServer.run_sse()` builds a Starlette MCP HTTP+SSE server around `mcp.server.sse.SseServerTransport`. The server exposes `/sse` and… | ||
| CVE-2026-56833 | hig | 0.45 | — | — | Jun 18, 2026 | # PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal ## Summary PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing: -… | ||
| CVE-2026-56832 | hig | 0.45 | — | — | Jun 18, 2026 | # DiscordApproval accepts unrelated channel messages as dangerous-tool approvals ## Summary `praisonai.bots.DiscordApproval` approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval,… | ||
| CVE-2026-61446 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py) files from project-level and user-home .praisonai/plugins/ directories using importlib spec_from_file_location() and… | |||
| CVE-2026-61443 | 0.00 | — | 0.01 | Jul 15, 2026 | PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run_skill_script() that executes scripts without path containment validation. Attackers can supply absolute file paths to execute arbitrary scripts from any filesystem location, including those… | |||
| CVE-2026-61440 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI Platform before 0.1.9 fails to properly authorize label and issue-label mutations, allowing workspace members to rename and recolor shared labels and add or remove labels on owner-created issues. Attackers with workspace member privileges can exploit PATCH and… | |||
| CVE-2026-61435 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI before 4.6.78 contains an authentication bypass in the Call API agent invocation endpoints (src/praisonai/praisonai/api/agent_invoke.py) when PRAISONAI_CALL_AUTH=disabled is configured. The safeguard intended to restrict the disabled-auth opt-out to localhost binding… | |||
| CVE-2026-61433 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI before 4.6.78 fails to safely encode deployment configuration values when generating Python source code for API servers. Attackers can inject arbitrary Python expressions through the deploy.api.host and agents_file configuration parameters that execute when the… | |||
| CVE-2026-61430 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI before 1.6.78 contains a server-side request forgery vulnerability in the web_crawl tool that validates hostnames at check time but re-resolves them at connection time without IP pinning. Attackers can use DNS rebinding to bypass SSRF protection and retrieve internal… | |||
| CVE-2026-61427 | 0.00 | — | 0.00 | Jul 15, 2026 | PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve… |
- risk 0.45cvss —epss —
### Summary Setting `PRAISONAI_CALL_AUTH=disabled` completely disables all authentication on the `/api/v1/agents/{id}/invoke` endpoint. This bypass is advertised in the application's own error messages, making it likely to appear in production Docker and Compose configurations. …
- risk 0.45cvss —epss —
### Summary A Server-Side Request Forgery (SSRF) vulnerability in the SearxNG / `search_web` search tools allows an attacker to make the server perform requests to arbitrary internal endpoints and read the responses back. The `searxng_url` argument is passed directly to…
- risk 0.45cvss —epss —
## Summary PraisonAI's template loader accepts GitHub template URIs with refs, for example `github:owner/repo/[email protected]`. The resolver stores the user-controlled template path and ref verbatim, and the cache layer later joins those values into…
- risk 0.45cvss —epss —
### Summary An unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the `agent_file` field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. ### Details The…
- risk 0.45cvss —epss —
# PraisonAI `recipe.run_stream()` skips dangerous-tool policy enforcement ## Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes `allow_dangerous_tools=True`. The normal `recipe.run()` path enforces this with…
- risk 0.45cvss —epss —
# HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools ## Summary `praisonai.bots.HTTPApproval` renders pending tool approval arguments directly into the approval dashboard HTML. An attacker-controlled tool argument…
- risk 0.45cvss —epss —
# PraisonAI LinearBot processes unsigned webhooks when `LINEAR_WEBHOOK_SECRET` is missing ## Summary PraisonAI's LinearBot starts a public webhook listener on `0.0.0.0` and treats `LINEAR_WEBHOOK_SECRET` as optional. When the secret is absent, startup only logs a warning and…
- risk 0.45cvss —epss —
# PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage ## Summary PraisonAI's Dynamic Context Discovery feature exposes artifact helper tools through `ctx.get_tools()`: ```python ctx = setup_dynamic_context() agent = Agent( …
- risk 0.45cvss —epss —
# PraisonAI Slack `app_mention` bypasses configured user/channel authorization ## Summary PraisonAI's Slack bot applies its configured `allowed_users`, `allowed_channels`, and unknown-user pairing policy in the normal Slack `message` event handler, but not in the adjacent…
- risk 0.45cvss —epss —
# PraisonAI `recipe serve` Typer command bypasses the non-localhost authentication guard ## Summary PraisonAI's installed console entrypoint is Typer-first. In current releases, the `recipe` command is registered in the Typer app and `praisonai recipe serve` dispatches to the…
- risk 0.45cvss —epss —
# PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools ## Summary `praisonaiagents.mcp.ToolsMCPServer.run_sse()` builds a Starlette MCP HTTP+SSE server around `mcp.server.sse.SseServerTransport`. The server exposes `/sse` and…
- risk 0.45cvss —epss —
# PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal ## Summary PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing: -…
- risk 0.45cvss —epss —
# DiscordApproval accepts unrelated channel messages as dangerous-tool approvals ## Summary `praisonai.bots.DiscordApproval` approves a pending dangerous tool call when it sees any later non-bot message in the configured Discord channel whose text is classified as approval,…
- CVE-2026-61446Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py) files from project-level and user-home .praisonai/plugins/ directories using importlib spec_from_file_location() and…
- CVE-2026-61443Jul 15, 2026risk 0.00cvss —epss 0.01
PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run_skill_script() that executes scripts without path containment validation. Attackers can supply absolute file paths to execute arbitrary scripts from any filesystem location, including those…
- CVE-2026-61440Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI Platform before 0.1.9 fails to properly authorize label and issue-label mutations, allowing workspace members to rename and recolor shared labels and add or remove labels on owner-created issues. Attackers with workspace member privileges can exploit PATCH and…
- CVE-2026-61435Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI before 4.6.78 contains an authentication bypass in the Call API agent invocation endpoints (src/praisonai/praisonai/api/agent_invoke.py) when PRAISONAI_CALL_AUTH=disabled is configured. The safeguard intended to restrict the disabled-auth opt-out to localhost binding…
- CVE-2026-61433Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI before 4.6.78 fails to safely encode deployment configuration values when generating Python source code for API servers. Attackers can inject arbitrary Python expressions through the deploy.api.host and agents_file configuration parameters that execute when the…
- CVE-2026-61430Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI before 1.6.78 contains a server-side request forgery vulnerability in the web_crawl tool that validates hostnames at check time but re-resolves them at connection time without IP pinning. Attackers can use DNS rebinding to bypass SSRF protection and retrieve internal…
- CVE-2026-61427Jul 15, 2026risk 0.00cvss —epss 0.00
PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve…
Page 1 of 2