harness-diagnostics
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files (e.g., project documentation and configuration files) to perform its diagnostics, which creates a potential surface for instructions embedded in those files to influence agent behavior.
- Ingestion points: Files are read using
Read,Grep, andGlobtools across the project structure (SKILL.md). - Boundary markers: None identified; instructions do not explicitly wrap ingested content in delimiters or ignore embedded instructions.
- Capability inventory: The skill has access to
Bash,Read,Grep, andGlobwhich allow for file system interaction and shell execution (SKILL.md). - Sanitization: No specific sanitization or filtering of the file content is described before processing.
Audit Metadata