issue-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 Composio to pull issue data from Linear/Jira (outsider-authored issue titles/summaries/comments) via composio execute ... and then the agent processes that text locally (clustering/deduping and composing Slack digests), so outsider free text is ingested into the LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The Prereqs instruct running "curl -fsSL https://composio.dev/install | bash", which fetches and immediately executes remote code from https://composio.dev/install as a required install step.