geo-citability
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from target URLs to perform scoring and rewrite suggestions. \n
- Ingestion points: Target website content retrieved via WebFetch in Step 1. \n
- Boundary markers: The procedure lacks explicit markers or delimiters to separate external content from instructions. \n
- Capability inventory: The skill possesses Bash, Write, and WebFetch capabilities. \n
- Sanitization: No sanitization or escaping of external content is specified before processing. \n- [COMMAND_EXECUTION]: The skill utilizes shell commands to retrieve site metadata during the audit process. \n
- Evidence: The example section in SKILL.md shows the use of
curlvia the Bash tool to fetchrobots.txtandllms.txt. \n- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch content from remote servers for analysis. \n - Evidence: The analysis procedure (Step 1) involves retrieving the full text content of a target URL using WebFetch.
Audit Metadata