geo-citability
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external websites, creating a surface for potential indirect prompt injection.
- Ingestion points: Data enters the agent's context through the
WebFetchtool during the initial retrieval of page content (Step 1). - Boundary markers: The instructions lack the use of clear delimiters or specific directives to ignore embedded instructions within the fetched content.
- Capability inventory: The skill has access to several powerful tools, including
Bash,Write,Read,Grep, andGlob, which could be targeted by instructions hidden in the processed data. - Sanitization: There is no evidence of content sanitization, filtering, or validation to ensure that the retrieved data does not contain malicious prompts or commands.
Audit Metadata