lead-research-assistant

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted data from external websites and local repository files without implementing security boundaries.
  • Ingestion points: External company websites, job listings, and news articles identified during research, as well as the local codebase files analyzed to understand the product context.
  • Boundary markers: The instructions lack delimiters or specific directives to ignore instructions that might be embedded within the external content being processed.
  • Capability inventory: The agent utilizes filesystem read and write access (to analyze the codebase and save CSV files) and network access to perform research.
  • Sanitization: There are no instructions to sanitize or validate the external data before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — lead-research-assistant