money-find

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by fetching and processing untrusted external data from the web.
  • Ingestion points: Untrusted data enters the context via the WebSearch and WebFetch tools during Step 1, where the agent retrieves recruitment data, market reports, and policy updates from third-party websites.
  • Boundary markers: The instructions do not specify any delimiters or boundary markers to isolate external web content from the agent's primary instructions.
  • Capability inventory: The skill has access to powerful tools including Bash(*), Write, Edit, and Skill, which increases the potential impact if a prompt injection attack were successful.
  • Sanitization: There is no requirement or logic provided for the agent to sanitize, escape, or validate the fetched data before it is interpreted and analyzed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 03:03 PM
Security Audit — agent-trust-hub — money-find