plan-launch
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructional guidelines for app launch planning. It does not contain executable code, command injections, or data exfiltration patterns. It explicitly prohibits the agent from taking autonomous external actions like social media posting or App Store submissions without user confirmation.
- [PROMPT_INJECTION]: The skill identifies potential ingestion of external information such as competitor claims and app reviews. It implements security best practices by instructing the agent to treat these sources as untrusted inputs that must be corroborated.
- Ingestion points: External web pages, competitor claims, and app reviews mentioned in references/04-discovery-listing.md.
- Boundary markers: Explicit instructions to gate public actions and treat external data as untrusted are present in SKILL.md and references/04-discovery-listing.md.
- Capability inventory: The skill refers to auxiliary tools (design-screenshots, aso-pass) but does not include direct network or file-write capabilities.
- Sanitization: Includes specific instructions to corroborate external evidence before accepting marketing claims or outcomes.
Audit Metadata