lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and qualifies leads by searching for and processing external data such as job postings, company news, and website content. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data the agent retrieves.
- Ingestion points: External search results, company websites, and job postings are ingested to fulfill the lead research request as specified in the 'Research and Identify Leads' section of SKILL.md.
- Boundary markers: The skill lacks explicit instructions to treat external data as untrusted or to use boundary markers (delimiters) for segregation.
- Capability inventory: The skill instructions direct the agent to perform file-read operations (to analyze the local codebase) and network searches to gather intelligence on target companies.
- Sanitization: There are no instructions provided for sanitizing or validating the content retrieved from external sources before it is processed by the agent.
Audit Metadata