github-roadmap-strategist
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and operationalize GitHub Issues, which serve as external data sources that could potentially contain malicious or untrusted content.
- Ingestion points: GitHub Issues (Repository Issues) identified as the 'Backlog' in
SKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the agent when reading issue content.
- Capability inventory: The skill instructs the agent to configure GitHub Actions (e.g.,
actions/github-script) that execute logic based on issue events, as seen inreferences/governance-protocols.md. - Sanitization: The skill proactively addresses data exposure risks via the 'Shadow Items' pattern in
references/governance-protocols.md, which mandates sanitization of issues before they are synced to public repositories. - [EXTERNAL_DOWNLOADS]: The skill references official and well-known GitHub Actions for automation tasks within its documentation templates.
- Evidence:
references/workflow-integration.mdincludes a template utilizingactions/github-script@v7, which is a trusted, official repository from the GitHub organization.
Audit Metadata