lead-research
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to research accounts and contacts by ingesting data from external sources like LinkedIn, Crunchbase, and job boards.
- Ingestion points: External data sources including social media, financial databases, and job postings (SKILL.md).
- Boundary markers: None; the instructions do not specify delimiters or warnings for the agent to ignore embedded instructions in the research data.
- Capability inventory: No code or scripts are included in the skill itself; the agent uses its primary browsing and file-access capabilities to perform the described tasks.
- Sanitization: The skill lacks explicit instructions for sanitizing or validating data retrieved from the web.
- [NO_CODE]: The skill consists entirely of natural language instructions and Markdown templates without any embedded scripts or executable code.
Audit Metadata