geo-llmstxt
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 by fetching llms.txt files and website content from arbitrary domains to perform validation and generation tasks.
- Ingestion points: Content retrieved via the WebFetch tool from website roots, navigation links, and sitemaps (SKILL.md).
- Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to treat fetched web content as untrusted data that should not be interpreted as instructions.
- Capability inventory: The skill is configured with access to tools including Bash (shell execution), Write (file system modification), and WebFetch (network access).
- Sanitization: There are no specified sanitization procedures to filter or escape instructions that might be embedded within the crawled website content or existing llms.txt files.
Audit Metadata