docs-launch-kit
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external repository files to generate launch copy, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads
CHANGELOG.md,README.md,package.json, and git release diffs to gather facts. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested files are defined in the procedure.
- Capability inventory: The skill is designed to write new markdown files to the
docs/launch/directory. - Sanitization: There is no evidence of input validation or content filtering for the data extracted from the repository files before it is processed by the model.
Audit Metadata