skills/richardbray/skills/sync-docs/Gen Agent Trust Hub

sync-docs

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository being analyzed, which could contain malicious instructions. 1. Ingestion points: Project file contents and git diffs are read into the agent context during the documentation sync workflow. 2. Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or to ignore instructions embedded within project files. 3. Capability inventory: The skill has permissions to write to documentation files and execute shell commands such as git, grep, and local build scripts. 4. Sanitization: Absent. The instructions do not specify any validation or sanitization of ingested content.
  • [COMMAND_EXECUTION]: The workflow involves running build scripts defined within the target project to verify the documentation build.
  • [EXTERNAL_DOWNLOADS]: The skill is installed from the vendor's GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:20 AM
Security Audit — agent-trust-hub — sync-docs