The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and processes external project files from directories such as storage/specs/, storage/design/, src/, and tests/. While necessary for auditing, these files are untrusted data sources.
Ingestion points: The skill reads content from requirements.md, design.md, tasks.md, source code, and test files using the Read and Grep tools.
Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for the agent when processing the content of these files.
Capability inventory: The agent uses Read, Glob, and Grep to analyze files and writes traceability reports in markdown format. It does not execute the contents of the audited files.
Sanitization: No explicit sanitization or validation of the ingested file content is mentioned before it is processed for reporting.

traceability-auditor