team-manager

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages GitHub organization teams and membership permissions through designated platform tools. It enforces manual confirmation prompts before executing any changes to ensure user oversight.
  • [PROMPT_INJECTION]: The skill processes external data from the GitHub API, such as usernames and issue titles, creating a surface for indirect prompt injection. Ingestion points: GitHub REST/GraphQL API responses (usernames, PR titles). Boundary markers: Not explicitly used. Capability inventory: Team membership modification and organizational role management. Sanitization: Not explicitly defined for API-fetched strings. The risk is significantly reduced by the mandatory manual confirmation steps before any actions are performed based on this data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — team-manager