The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md and README.md) and does not include any executable scripts, binaries, or configuration files that could run on the host system.
[SAFE]: The skill's operations are strictly limited to the local project directory, specifically the outputs/prds/ folder and the PRD-PIPELINE.md file at the root. It does not attempt to access sensitive system directories (e.g., .ssh, .aws) or environment variables.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes content from externally generated files. However, given its limited capabilities, the risk is minimal.
Ingestion points: The skill reads outputs/prds/[prd-name].md and outputs/prds/[prd-name]-review-synthesis.md to verify status and pull summary information.
Boundary markers: Absent; the skill directly extracts and displays lines like "Overall Assessment" from the synthesis file.
Capability inventory: The skill is restricted to reading and writing local markdown files within the project workspace.
Sanitization: No explicit sanitization or escaping of the ingested file content is performed before it is presented to the user.

prd-approve