The Agent Skills Directory

[SAFE]: The skill's operations, including searching files and executing local tests, are entirely consistent with its stated purpose of auditing test isolation and anti-patterns. No evidence of obfuscation, exfiltration, or unauthorized privilege escalation was found.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze untrusted codebase content.
Ingestion points: The skill reads project files using Read, Grep, and Glob tools as part of the Audit Rules and Workflow steps.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the analyzed code.
Capability inventory: The skill has access to Bash for running tests and Write for generating markdown reports in an output directory.
Sanitization: No sanitization of the ingested code content is described in the provided logic.
Note: This surface is an inherent requirement for the skill's function as a code auditor and is documented for architectural awareness.

ln-635-test-isolation-auditor