geo-llmstxt
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data fetched from external websites via WebFetch. This creates a potential surface for indirect prompt injection where instructions embedded in a target website could attempt to influence the agent's behavior during analysis or generation.
- Ingestion points: Website content and llms.txt files fetched from user-provided domains via WebFetch as described in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are defined to separate the fetched content from the agent's internal logic.
- Capability inventory: The skill utilizes WebFetch for data ingestion and Write to generate reports; it also requests Bash tool access.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from the web.- [COMMAND_EXECUTION]: The skill requests access to the Bash tool in its configuration metadata, although no specific shell scripts or complex command strings are provided within the instruction body.- [EXTERNAL_DOWNLOADS]: The skill is designed to perform network operations using WebFetch to retrieve content from arbitrary external domains as part of its core discovery and analysis functionality.
Audit Metadata