The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for generating PRDs. It does not include any executable code, scripts, or tool definitions. The instructions focus on document quality and technical specification structure.
[CREDENTIALS_UNSAFE]: The example configuration snippets in SKILL.md and references/examples.md contain placeholder credentials (e.g., "your-secret-key", "user:pass", "SG.xxx"). These are documented as illustrative examples for user configuration and do not represent actual exposed secrets.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user requirements to generate technical documentation. While it lacks explicit boundary markers and sanitization, the impact is negligible as the skill has no dangerous capabilities (such as shell access, file writing, or network tools).
Ingestion points: User requirements and planner outputs in SKILL.md description.
Boundary markers: Absent.
Capability inventory: None (text-generation only).
Sanitization: Absent.

prd-authoring