The Agent Skills Directory

[SAFE]: The skill instructions and associated scripts follow established patterns for automated codebase auditing. The logic focuses on calculating test metrics and generating reports locally. No evidence of malicious behavior, data exfiltration, or unauthorized command execution was found.
[PROMPT_INJECTION]: The skill processes test code from the project codebase to perform its analysis. This creates a surface for indirect prompt injection if the files under audit contain adversarial instructions. However, this is a inherent risk for any code-analysis tool and is mitigated by the agent's internal safety filters.
Ingestion points: codebase test files (specified in SKILL.md Workflow).
Boundary markers: None explicitly defined.
Capability inventory: Read, Grep, Glob, Bash, and Write tools.
Sanitization: Not explicitly defined in the prompt logic.

ln-633-test-value-auditor