The Agent Skills Directory

[SAFE]: The skill operates as a legitimate development tool for auditing test coverage, with no detected malicious patterns such as data exfiltration, obfuscation, or unauthorized command execution.
[PROMPT_INJECTION]: The skill possesses an inherent surface for indirect prompt injection because its primary function is to read and analyze untrusted codebase content. However, this is consistent with its stated purpose as an auditor. The risk is mitigated by the methodology's requirement for Layer 2 context analysis, which uses agent reasoning to filter findings.
Ingestion points: Codebase files are ingested via Read and Grep tools as defined in the workflow (SKILL.md) and detection methodology (references/two_layer_detection.md).
Boundary markers: The skill does not explicitly define unique boundary markers for the code snippets it interpolates into its reasoning context.
Capability inventory: The skill utilizes Read, Grep, Glob, Bash, and Write tools to perform its audit and generate reports.
Sanitization: The 'Two-Layer Detection' strategy acts as a sanitization layer where the agent is instructed to analyze surrounding code context and dismiss false positives before reporting findings.

ln-632-test-e2e-priority-auditor