The Agent Skills Directory

[SAFE]: The skill operates as a read-only auditor, scanning local project files for completeness based on a predefined registry. It does not attempt to modify existing files or perform any write operations other than generating an optional markdown report.
[SAFE]: No network-enabled tools or remote code execution patterns were identified. All data processing is local to the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project documents (PRDs, DR Plans, etc.) to assess their content. Although this represents an attack surface, the risk is negligible because the skill does not expose sensitive data or execute instructions found within those documents.
[SAFE]: The templates provided are standard markdown structures with placeholders for project-specific metadata and do not contain malicious scripts or hidden content.

pmstudio-nfr