feature-manager
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external GitHub sources, which creates a potential surface for indirect instructions.
- Ingestion points: The
discover-feature.shscript reads GitHub issue bodies, andfeature-feedback.shfetches comment and review bodies from issues and PRs. - Boundary markers: While the skill uses specific markers for syncing issue bodies, it does not consistently use delimiters to wrap all external data shown to the agent.
- Capability inventory: The skill possesses capabilities to perform git operations (
git checkout,git merge,git pushincascade-update.sh) and modify GitHub issues (gh issue editin the Sync Issue chore). - Sanitization: The skill mitigates risks by requiring explicit user confirmation before writing registry files or performing git merges, and routes all outgoing GitHub modifications through a
post-review-gatefor final oversight.
Audit Metadata