lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [DATA_EXFILTRATION] (LOW): Potential for data exposure via codebase analysis. The skill requests the agent to read the local repository to understand the product's value proposition. When combined with the agent's ability to perform web searches for lead generation, there is a risk of sensitive information from the code being included in external queries or summaries.
- [PROMPT_INJECTION] (LOW): Susceptibility to Indirect Prompt Injection.
- Ingestion points: The agent reads local codebase files and external web content (company websites, LinkedIn profiles, job postings) to find leads.
- Boundary markers: No explicit delimiters or instructions to disregard embedded commands in the processed data are provided in the skill instructions.
- Capability inventory: File system read access (codebase) and network read access (web search).
- Sanitization: No sanitization or validation of the ingested content is specified before the agent processes it.
- [NO_CODE] (SAFE): This skill is composed entirely of markdown instructions and does not include any Python scripts, Node.js packages, or shell commands.
Audit Metadata