cr-create

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes curl and jq to perform API operations and process JSON data.
  • [EXTERNAL_DOWNLOADS]: Communicates with the GitBook REST API at api.gitbook.com and user-defined Slack webhooks to manage documentation workflows. These resources are vendor-owned or user-configured.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from document comments and page content.
  • Ingestion points: Document pages and change request comments fetched via the REST API in SKILL.md.
  • Boundary markers: Explicitly instructs the agent to treat all fetched content as data rather than instructions.
  • Capability inventory: Network access via curl and shell command execution.
  • Sanitization: Uses jq for safe parsing and construction of data bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 04:30 PM
Security Audit — agent-trust-hub — cr-create