claude-docs-consultant

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill fetches documentation from code.claude.com. While this is the official site for Claude Code documentation, the domain is not included in the predefined whitelist of trusted organizations, which results in a low-severity finding for external network operations.
  • [DATA_EXFILTRATION] (SAFE): No sensitive file access (e.g., SSH keys, AWS credentials) or hardcoded secrets were detected. The network operations are limited to fetching documentation and do not transmit user data.
  • [REMOTE_CODE_EXECUTION] (SAFE): The skill retrieves Markdown files for reference and does not attempt to execute the fetched content, install external packages, or use dynamic execution functions like eval() or exec().
  • [INDIRECT_PROMPT_INJECTION] (LOW): This skill exhibits an ingestion surface for untrusted data from an external source.
  • Ingestion points: External Markdown files fetched via WebFetch from code.claude.com (SKILL.md).
  • Boundary markers: Absent. There are no instructions or delimiters to ensure the agent treats the fetched documentation as passive data.
  • Capability inventory: No dangerous capabilities (such as file-writing or subprocess execution) are present in this skill.
  • Sanitization: Absent. The skill does not provide logic to sanitize or validate the content retrieved from the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM