geo-crawlers
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from websites, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The analysis procedure instructs the agent to fetch and parse content from
robots.txt, HTML meta tags, and HTTP headers using theWebFetchtool (SKILL.md). - Boundary markers: The instructions do not define any delimiters or system-level directives to treat the retrieved external content strictly as data, leaving the agent vulnerable to embedded natural language instructions.
- Capability inventory: The skill is granted access to powerful tools including
Bash,Write,Read, andGrep(SKILL.md), which increases the potential impact of a successful injection attack. - Sanitization: The skill lacks any requirements for sanitizing, escaping, or validating the external content before it is incorporated into the agent's context.
Audit Metadata