sentry-triage

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required workflow uses the Composio CLI to fetch Sentry issue/event data (outsider-authored text from the Sentry project) and then the agent reads stack frame filename/lineno content into its LLM context, creating an indirect prompt-injection path via Sentry-provided fields and stack traces.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite runs a remote install script via curl -fsSL https://composio.dev/install | bash which downloads and immediately executes remote code (https://composio.dev/install), making it a runtime external dependency that executes code.