skill-matrix-author
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources like test strategies and project roadmaps to generate reports, presenting an attack surface for instructions hidden in those artifacts.
- Ingestion points: Team rosters, test strategies, and project roadmaps as defined in SKILL.md Step 1.
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill performs file system write operations to generate gap reports in the docs directory.
- Sanitization: There are no instructions provided for sanitizing or escaping the content of processed project artifacts.
- [EXTERNAL_DOWNLOADS]: The skill references official certification syllabi and terminology glossaries from professional testing organizations (astqb.org and istqb.org).
Audit Metadata