lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which could contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: The skill reads local files during codebase analysis (SKILL.md) and retrieves content from external websites via web search tools to identify leads and signals.
- Boundary markers: There are no specific instructions or delimiters defined to isolate the ingested external content or to prevent the agent from following commands embedded within that content.
- Capability inventory: The skill has access to file reading tools for codebase analysis and web search tools for company research.
- Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from the web or local files before it is processed by the agent.
Audit Metadata