launch-tier-planner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data which could contain malicious instructions.
- Ingestion points: The skill reads user-provided context, project files, and public/connected data sources (scraped page text, reviews, comments, emails) as defined in SKILL.md.
- Boundary markers: The instructions explicitly state in both SKILL.md and references/skill-contract.md to treat external text as untrusted and not to follow embedded instructions from evidence.
- Capability inventory: The skill references connectors for search, SEO, and marketing execution tools (Google Ads, HubSpot, Slack) that could be manipulated via poisoned data.
- Sanitization: The skill relies on natural language instructions for the agent to ignore embedded commands rather than programmatic filtering.
Audit Metadata