Composio Connect

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to fetch, read, analyze, and act on data from external applications (e.g., Slack, GitHub, Gmail) via the Composio CLI, meaning it will consume untrusted/user-generated third‑party content that can influence subsequent tool actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs users to run "curl -fsSL https://composio.dev/install | bash", which fetches and executes remote code from https://composio.dev/install at setup/runtime and the Composio CLI installed by that script is relied on by the skill.