feature-launch-playbook
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external feature specifications and PRDs to generate marketing assets, creating a surface for indirect prompt injection.
- Ingestion points: Intake phase (Phase 0) in SKILL.md accepts feature names, descriptions, and external Notion/PRD excerpts.
- Boundary markers: The skill does not define explicit delimiters or boundary instructions to separate untrusted data from its asset templates.
- Capability inventory: The skill utilizes file-writing capabilities to save generated assets to the filesystem in Phase 4 of SKILL.md.
- Sanitization: No sanitization or input validation logic is present for the ingested data before it is interpolated into templates.
Audit Metadata