manager

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could contain malicious instructions designed to influence the agent. 1. Ingestion points: The agent reads GitHub issue titles, bodies, labels, and Project board data (SKILL.md). 2. Boundary markers: The skill uses specific markdown templates for updates and follows strict 'Iron Invariants' to structure its output. 3. Capability inventory: The skill can create and edit issues, post comments, and modify project boards via the gh CLI (SKILL.md). 4. Sanitization: Instructions are provided to strip private information (paths, slugs, handles) before writing to public repositories (SKILL.md).
  • [COMMAND_EXECUTION]: The skill relies on shell commands for its core operations, which is expected for its purpose but involves interaction with the host environment. Evidence: Uses gh for GitHub API calls, git for repository metadata, jq for JSON processing, and date for time calculations (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 04:26 AM
Security Audit — agent-trust-hub — manager