targeted-prospecting
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its web scraping workflows.
- Ingestion points: External websites such as company leadership pages, job boards, and competitor sites are scraped using scrapegraph and tavily in Steps 4, 6, and 7.
- Boundary markers: The instructions do not define boundary markers or delimiters to isolate untrusted web content from the agent's internal logic.
- Capability inventory: The agent utilizes multiple network-based APIs including Fiber, Sixtyfour, Hunter, Tomba, and Nyne to retrieve, enrich, and verify prospect data.
- Sanitization: There is no evidence of sanitization or validation logic to filter potentially malicious instructions embedded in the scraped HTML or text content.
Audit Metadata