The Agent Skills Directory

[SAFE]: No malicious patterns, unauthorized data access, or dangerous execution triggers were identified. All operations are confined to the local project directory and standard requirements engineering workflows.
[PROMPT_INJECTION]: The skill features a workflow for ingesting user-provided documentation (RFCs, feature briefs, notes). While this constitutes an ingestion surface for indirect prompt injection, the risk is effectively mitigated by the skill's design, which converts unstructured input into a strictly validated YAML schema before persistence. No instructions to bypass safety guidelines were found.
[COMMAND_EXECUTION]: The skill utilizes a bundled Python script (scripts/validate_requirements.py) to validate requirement consistency and generate Mermaid diagrams. Technical review of the script confirms it performs safe YAML parsing (using yaml.safe_load), performs local graph analysis, and writes to local paths without utilizing network resources or dynamic code execution (eval/exec).
[DATA_EXPOSURE]: The skill operates exclusively on requirements artifacts (YAML, Markdown, Mermaid). No patterns of sensitive file access, credential harvesting, or external data exfiltration were detected.

requirements-engineering