lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the local codebase and external GitHub repositories to understand product value propositions and identify leads.
- Ingestion points: The agent reads files from the local directory/repository and searches through external GitHub repositories to identify technical signals, as described in
SKILL.md. - Boundary markers: The instructions lack clear delimiters or specific directives to ignore instructions embedded within the analyzed codebase or external repository files.
- Capability inventory: The skill utilizes web search capabilities to identify companies and decision-makers, provides LinkedIn URLs, and offers to save lead data to CSV files.
- Sanitization: There are no instructions for sanitizing or validating the content read from the codebase or external sources, which could allow malicious instructions in code comments or documentation to influence the agent's behavior during search or outreach generation.
Audit Metadata