gsd-add-tests
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes information from external project files to drive its test generation and verification workflow, which can be exploited if those files contain malicious instructions.\n
- Ingestion points: Documentation files
SUMMARY.md,CONTEXT.md, andVERIFICATION.md(specified in the objective) are ingested to provide specifications for generating tests.\n - Boundary markers: No explicit boundary markers or "ignore instructions" warnings are defined to separate ingested data from the skill's operational instructions.\n
- Capability inventory: The skill is granted access to powerful tools including
Write,Edit, andBash, which could be misused if the agent obeys instructions hidden within the spec files.\n - Sanitization: There is no mentioned process for sanitizing or validating the content of the ingested markdown files before the agent acts upon them.
Audit Metadata