startup-fundraising

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the agent to perform a directory listing of local skill paths (e.g., ~/.claude/skills/) using the ls command to identify which companion skills are currently installed for recommendation purposes.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing additional companion modules from the AbsolutelySkilled repository using the npx skills add command. These are vendor-provided resources related to the primary functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted external data, such as investor pitch decks or term sheets.
  • Ingestion points: Processes user-provided fundraising documents, spreadsheets, and data rooms (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when processing document content.
  • Capability inventory: File system listing (ls) and package installation (npx).
  • Sanitization: No specific sanitization or validation of the ingested external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:04 PM
Security Audit — agent-trust-hub — startup-fundraising