lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on gathering and analyzing data from the open web, creating a potential surface for indirect prompt injection via external content.
- Ingestion points: The skill researches companies by reading untrusted data sources including job postings, technology stacks, and recent news (SKILL.md, Instructions step 3).
- Boundary markers: The instructions lack specific boundary markers or directives for the agent to ignore instructions potentially embedded within the searched web content.
- Capability inventory: The agent utilizes search tools and text analysis to generate lead reports, scores, and outreach strategies.
- Sanitization: There is no evidence of sanitization, filtering, or validation applied to the external data before it is processed by the agent.
Audit Metadata