anysite-vc-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external websites (via
webparser), pitch decks (viaWebFetch), and LinkedIn profiles. This content is used to drive the agent's scoring logic and outreach generation without explicit security boundaries.\n - Ingestion points: External data is ingested from company websites (via
webparser), pitch deck URLs (viaWebFetch), and investor profiles (vialinkedintool).\n - Boundary markers: The instructions lack specific delimiters or "ignore embedded instructions" directives for the fetched content.\n
- Capability inventory: The skill has access to tool execution (
execute), file reading (Read), web searching (WebSearch), and data exporting (export_data).\n - Sanitization: There are no defined mechanisms to sanitize or validate the content retrieved from external sources before it enters the agent's context.
Audit Metadata