lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by instructing the agent to ingest and process data from untrusted sources.
- Ingestion points: The agent is directed to analyze the current codebase in the local directory and perform web searches to identify signals like job postings, company news, and repository content.
- Boundary markers: There are no instructions to use delimiters or explicit warnings to prevent the agent from following instructions potentially embedded within the analyzed codebase or external search results.
- Capability inventory: The skill has access to file reading (codebase analysis), network operations (web search), and file writing (CSV export).
- Sanitization: No sanitization or validation logic is defined to filter malicious payloads that might be present in external company data or signals before they are processed by the agent.
Audit Metadata