connect
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of several packages from official registries (npm and PyPI), including 'composio', '@composio/core', and 'claude-agent-sdk', which are standard components for the platform described.
- [DATA_EXFILTRATION]: The skill's primary function is to move data between external services (e.g., summarizing GitHub issues to Slack). It utilizes an API key for authentication with the Composio platform, which is managed via environment variables.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources (Ingestion points: Gmail, Slack, GitHub, Notion) and has powerful write capabilities (Capability inventory: sending emails, updating databases). The provided implementation does not show explicit boundary markers or sanitization logic to mitigate instructions embedded in the external data (Evidence: missing delimiters in the Python code snippet).
Audit Metadata