ln-633-test-value-auditor
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes test files and metadata from the codebase it audits. This creates a surface for indirect prompt injection, where an attacker could embed malicious instructions in test descriptions or comments to influence the agent's behavior, especially given its access to shell tools.
- Ingestion points:
testFilesMetadataand test file contents read during theParse ContextandCalculate Scoresworkflows. - Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions when interpolating audited content into its reasoning process.
- Capability inventory: The skill is allowed to use
Bash,Read,Grep, andGlobtools. - Sanitization: There is no evidence of content sanitization or validation for the test data processed during the audit.
Audit Metadata