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