sync-docs

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git status --porcelain and git diff commands to identify modified files in the local workspace.
  • [DYNAMIC_EXECUTION]: The skill runs a local script using node .agents/scripts/precheck.mjs to verify project categories and environment configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted repository metadata and file changes.
  • Ingestion points: File paths, names, and diff outputs processed from git commands.
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard potential instructions embedded within the file changes.
  • Capability inventory: Local script execution (node), command-line execution (git), and file system write access to documentation files and the project index.
  • Sanitization: No validation or sanitization of ingested repository data is mentioned prior to its use in documentation updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 04:25 AM
Security Audit — agent-trust-hub — sync-docs