accelint-skill-manager

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform local file system checks using ls -la to identify existing global or project-level skills before initialization. These are benign read-only operations restricted to the agent's skill directories.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation commands using npx and pnpm to fetch additional skills from the vendor's official GitHub repository (github.com/gohypergiant). These are standard package manager invocations targeting author-controlled infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied domain descriptions to generate instructions and workflows. While the agent has file-writing capabilities to create new skills, the provided templates and logic do not introduce unsafe interpolation of external data into high-privilege execution paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:44 AM