composio-activity-summary

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes untrusted data from external platforms to generate summaries.
  • Ingestion points: Data is fetched from Slack messages, GitHub pull requests and issues, Notion page contents, and Gmail email bodies using platform-integrated tools.
  • Boundary markers: The instructions for the sub-agents lack explicit delimiters or instructions to ignore potential commands embedded within the external content.
  • Capability inventory: The skill utilizes file system write operations to save summaries locally and executes various API-based read tools.
  • Sanitization: There is no evidence of filtering or sanitization of the fetched external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 04:42 PM
Security Audit — agent-trust-hub — composio-activity-summary