list-qa-tests
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from the filesystem.
- Ingestion points: Markdown files located in the
qa-tests/directory and its subdirectories. - Boundary markers: None. No explicit delimiters or instructions to ignore embedded commands are provided.
- Capability inventory: Scanning local directories and reading/parsing the content of markdown files.
- Sanitization: None. There are no instructions for escaping or validating the content extracted from the test files before processing.
- [NO_CODE]: The skill is comprised entirely of markdown instructions and does not ship with any executable scripts or binary files.
Audit Metadata