anysite-vc-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes vendor-specific tools (mcp__anysite__parse_webpage, mcp__anysite__get_linkedin_profile) for its core functionality of analyzing business websites and LinkedIn profiles. These resources are consistent with the 'anysiteio' author identity.
  • [SAFE]: Data persistence is handled locally via data/investor_criteria.json, which is a standard practice for maintaining session state and does not involve exfiltration of sensitive user information.
  • [SAFE]: The skill processes external data (websites and pitch decks), which creates a surface for indirect prompt injection; however, the agent's capabilities are restricted to analysis and text generation, minimizing potential impact. The skill documentation includes clear instructions for data ingestion points (Step 2 and Workflow Step 1) and inventory of capabilities (file reading and web fetching), fulfilling analysis transparency requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 08:46 PM