apm-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to process and triage external content, such as contributor Pull Requests and Issues.
- Ingestion points: The skill activates upon changes to community-facing files (
README.md,CHANGELOG.md) and instructs the agent to triage "External-contributor PRs/issues." - Capability inventory: The skill utilizes the
ghCLI to gather project evidence (stars, traffic, etc.) and serves as an arbiter for strategic decisions within the development workflow. - Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious instructions embedded in the external content being triaged.
- Sanitization: The instructions do not define specific sanitization or validation steps for the metadata or text contained within external GitHub contributions.
Audit Metadata