anfra-docs

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and specific URLs to fetch documentation indices (llms.txt) and markdown pages from anfra.ai and amql.org. These represent official domains for the product documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest content from external sources, creating a surface for potential indirect prompt injection. 1. Ingestion points: Markdown content and indices fetched from amql.org and anfra.ai URLs defined in SKILL.md. 2. Boundary markers: None specified in the instructions to separate fetched content from system prompts. 3. Capability inventory: The skill is restricted to documentation retrieval and does not employ subprocess execution, file-writing, or network posting capabilities. 4. Sanitization: No explicit sanitization or filtering of the external documentation content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 03:35 AM