geo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its reliance on untrusted external data.\n
- Ingestion points: The
WebFetchtool is used in Phase 1 to retrieve content from arbitrary user-provided URLs, including homepages, sitemaps, and internal links.\n - Boundary markers: The instructions do not define delimiters or provide guidance for the agent to ignore natural language instructions that might be hidden in the fetched HTML, meta tags, or structured data.\n
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andWebFetch, which increases the potential impact if the agent is manipulated via an injection.\n - Sanitization: There is no requirement or mechanism mentioned to sanitize, filter, or validate the retrieved content before it is analyzed by the parallel subagents in Phase 2.
Audit Metadata