connect-apps

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to install the composio-toolrouter plugin and acquire an API key from platform.composio.dev. These actions involve a well-known technology provider specialized in AI tool orchestration.
  • [COMMAND_EXECUTION]: The documentation includes standard commands for plugin installation (/plugin install) and configuration (/composio-toolrouter:setup) within the agent environment.
  • [PROMPT_INJECTION]: The skill's primary functionality involves processing data from external sources, which presents a surface for indirect prompt injection.
  • Ingestion points: External data retrieved from integrated services such as Gmail, Slack, and GitHub (SKILL.md).
  • Boundary markers: No explicit delimiters are mentioned in the instructions to separate external data from system instructions.
  • Capability inventory: The integration enables write operations including sending emails and creating platform issues (SKILL.md).
  • Sanitization: No sanitization methods for external content are described within the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:10 PM
Security Audit — agent-trust-hub — connect-apps