prospecting
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references integrations with various third-party data services (Apollo, Clay, ZoomInfo, Truelist, Clearbit, Hunter, Snov) and web extraction platforms (Firecrawl, Browserbase). These are standard tools for the skill's intended purpose of lead generation and enrichment.
- [COMMAND_EXECUTION]: Documentation within the skill references the use of a local command-line tool (
node tools/clis/github-prospects.js) to extract developer intent signals from GitHub. This is presented as an internal utility for the agent environment. - [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes data from external websites.
- Ingestion points: Researching and extracting content from individual prospect websites via browser-assisted tools (Firecrawl, Browserbase).
- Boundary markers: The instructions do not define specific delimiters for separating untrusted website content from the agent's internal reasoning.
- Capability inventory: The skill's capabilities are limited to data extraction, lead scoring, and table/CSV generation; it does not perform dangerous operations like code execution based on processed data.
- Sanitization: No explicit sanitization of website content is mentioned before it is processed by the agent.
Audit Metadata