wdk-review-tests
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external files, creating a surface for potential indirect prompt injection attacks where malicious code comments or strings could override agent behavior.
- Ingestion points: Files and directories provided via the
argument-hintor the current working directory. - Capability inventory: File read operations and text output generation.
- Boundary markers: None present; the skill lacks specific delimiters or 'ignore' instructions for data content.
- Sanitization: None present; the skill does not include logic to sanitize or escape file contents before processing.
Audit Metadata