launch-positioning-builder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from the internet, creating a surface for indirect prompt injection attacks.
- Ingestion points: In Phase 1A and 1B, the agent is instructed to use
fetch_webpageandweb_searchto retrieve content from competitor websites (homepages, pricing, about pages) and review platforms such as G2 or Capterra. - Boundary markers: The instructions do not provide delimiters or specific guidelines to the agent to treat the fetched content as data only or to ignore any potential instructions embedded within those external sources.
- Capability inventory: The skill utilizes network search and retrieval tools (
web_search,fetch_webpage) and has file-writing capabilities to save the final document to the local file system (e.g., in theclients/directory). - Sanitization: There are no instructions for validating, filtering, or sanitizing the content retrieved from external websites before it is used to generate the positioning framework and messaging.
Audit Metadata