systems-health
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill executes standard git and GitHub CLI commands (such as
git log,gh pr list, andgh issue list) to collect metadata for analysis. This behavior is consistent with the skill's primary purpose and does not involve unauthorized data access. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted content from commit messages via
git logand from PR/issue descriptions viagh pr listandgh issue list(SKILL.md). - Boundary markers: There are no explicit instructions to the agent to ignore embedded instructions within the gathered metadata.
- Capability inventory: The skill's capabilities are limited to reading repository metadata and writing a markdown report to a local file (
.tap/system-health.md). It lacks network access or code execution capabilities that could be exploited via injection. - Sanitization: No specific sanitization or filtering of the ingested external data is mentioned.
Audit Metadata