The Agent Skills Directory

[SAFE]: The skill is designed for document auditing and does not include any executable code, external scripts, or remote network operations.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted Markdown content from PRD files.
Ingestion points: The Read tool is used to load .prd.md files from the .trogonai/project/{projectid}/prd/ directory.
Boundary markers: No explicit delimiters or boundary markers are defined to isolate the ingested file content from the agent's core instructions.
Capability inventory: The agent has access to Read, Write, Glob, and Grep tools, which are necessary for its documented purpose.
Sanitization: No content validation or sanitization is performed on the ingested files prior to analysis.

prd-review