hol-guard

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes hol-guard and plugin-scanner commands to manage security approvals and audit AI harness activity.\n- [EXTERNAL_DOWNLOADS]: Recommends installing the hol-guard and plugin-scanner CLI tools via pipx. These tools are the primary resources provided by the skill author for security enforcement.\n- [INDIRECT_PROMPT_INJECTION]: The skill scans external directories and plugin packages, creating a surface for indirect prompt injection.\n
  • Ingestion points: plugin-scanner targets local paths and marketplace files in SKILL.md.\n
  • Boundary markers: Absent in the command instructions.\n
  • Capability inventory: Includes command execution and package installation.\n
  • Sanitization: Relies on the security logic of the scanner tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 04:25 PM