link-prospecting
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites and search engine results pages (SERPs) to extract contact details and editorial guidelines.\n
- Ingestion points: Data is collected from external prospect websites (contact pages, about/team pages) and SERP results via browsing tools.\n
- Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded in retrieved web content.\n
- Capability inventory: The skill utilizes capabilities to update project context, add competitors, and append entries to a research log based on the findings.\n
- Sanitization: No explicit sanitization or validation of external content is defined in the workflow.
Audit Metadata