docs-contribution-router

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for running various development and build commands.
  • Evidence: Files references/agent-connector-flow.md and references/api-reference-flow.md include commands such as pnpm run sync-agent-connectors, pnpm generate-search-index, and pnpm start.
  • Context: These commands are part of the intended documentation maintenance workflow for synchronizing metadata and building the site, and do not involve untrusted remote sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill routes actions based on contributor input, which presents a theoretical injection surface.
  • Ingestion points: Contributor intent strings (e.g., "I want to document X") are used to classify and branch logic in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the intent classifier.
  • Capability inventory: The skill can suggest file paths and shell command execution (via agent-connector-flow.md and api-reference-flow.md).
  • Sanitization: No input sanitization or validation of the contributor's stated intent is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:27 AM
Security Audit — agent-trust-hub — docs-contribution-router