ai-spec-coverage-mapper
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads specification files and test source code from the repository and interpolates them directly into a prompt for the LLM.
- Ingestion points: In
scripts/ai-coverage.py, the skill reads content from paths defined byspec_pathandtest_globs. - Boundary markers: The prompt construction in
scripts/ai-coverage.pylacks delimiters or instructions to the LLM to ignore embedded commands within the input data. - Capability inventory: The LLM's output is used to generate a coverage matrix and action items, which are subsequently used to create GitHub Issues in the provided CI workflow example.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the ingested file content before it is processed by the LLM.
Audit Metadata