offer-ladder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for malicious instructions to influence the agent.
- Ingestion points: Phase 1 instructions require the agent to scrape data from a user-provided 'Client website URL' using WebFetch or Apify and to pull content from Google Drive Docs.
- Boundary markers: The instructions do not specify any delimiters (like xml tags or triple backticks) or 'ignore' directives to prevent the agent from obeying commands embedded in the retrieved web content or documents.
- Capability inventory: The skill's capabilities are primarily analytical and text-generative (creating offer ladders, ICP maps, and launch sequences), which limits the impact of an injection, though it can still result in deceptive output or altered reasoning.
- Sanitization: There is no requirement or guidance for the agent to sanitize, filter, or validate the content retrieved from external sources before processing it.
Audit Metadata