docs-check
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted documentation files (e.g., markdown, ADRs) to verify their accuracy against the codebase. This creates an indirect prompt injection surface where instructions embedded in documentation could attempt to manipulate agent behavior.\n
- Ingestion points: Files within the docs/ directory and general codebase files parsed during relevance and technology stack checks.\n
- Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions for the content being analyzed.\n
- Capability inventory: The skill reads local files, utilizes git history for freshness checks, and references the execution of bash patterns for detailed verification tasks.\n
- Sanitization: No explicit sanitization, validation, or escaping of documentation content is described before processing or report generation.
Audit Metadata