gen-specs-as-issues
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from a project repository, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The workflow instructs the agent to read
README.md, project documentation, source code modules, and test files in theProject Understanding PhaseandGap Analysis Phase. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the project data and the agent's internal instructions.
- Capability inventory: The skill utilizes file reading capabilities to perform analysis and implies the use of GitHub issue creation tools to output its findings.
- Sanitization: There are no instructions provided to filter, validate, or sanitize the content of the project files before the agent processes them or includes them in generated issue specifications.
Audit Metadata