evidence-docs

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Bash script (templates/docgate.sh) intended for local use to audit documentation. It utilizes standard Unix utilities (grep, awk, sed, find) and git commands to verify link resolution and internal reference consistency. These operations are restricted to the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit markdown files, which theoretically exposes it to indirect prompt injection if those files contain malicious instructions. However, the risk is negligible as the skill lacks high-impact capabilities (such as network exfiltration or dangerous file writes) that could be abused via injected text.
  • [EXTERNAL_DOWNLOADS]: The documentation contains links to the author's GitHub repositories (github.com/ssheleg/...) and official service documentation (code.claude.com). These are identified as vendor-owned or well-known service resources and do not involve automated execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 12:33 AM