who-to-sell-to
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external, potentially untrusted data sources.
- Ingestion points: As noted in
SKILL.md, the agent reads deals lists, CRM exports, and researches companies by scraping public web pages. - Boundary markers: The instructions lack requirements for delimiters or specific commands to disregard instructions embedded in the external data.
- Capability inventory: The skill utilizes filesystem access to write an HTML report and network access for web searching and page fetching.
- Sanitization: There are no explicit steps for sanitizing or validating data retrieved from external files or websites before processing or report generation.
Audit Metadata