skills/dohooo/helmor/helmor-cli/Gen Agent Trust Hub

helmor-cli

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and commands for the Helmor CLI, which is used for local data and workspace management. All commands identified are part of the documented tool's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read external content via helmor files and helmor session and perform actions like sending prompts (helmor send) or managing GitHub repositories. This creates a surface for indirect prompt injection where malicious instructions in project files could influence the agent's behavior.
  • Ingestion points: Content read through helmor files and helmor session.
  • Boundary markers: None identified in the skill instructions to delimit untrusted file content.
  • Capability inventory: File reading/writing, GitHub integration (helmor github), and dispatching AI prompts (helmor send).
  • Sanitization: No specific sanitization or validation steps are prescribed for data ingested from the local file system or session history.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 02:40 PM