skills/neversight/skills_feed/harbor/Gen Agent Trust Hub

harbor

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Unverifiable Dependencies (LOW): The skill instructs the agent to install the harbor tool using uv tool install harbor. The source repository (laude-institute/harbor) is not within the predefined trusted organizations list.
  • Data Exposure (LOW): The documentation directs the agent to check .local-workspace/.env for sensitive API credentials such as ANTHROPIC_API_KEY. While this is standard for tool configuration, it explicitly guides the agent to access files containing secrets.
  • Indirect Prompt Injection (LOW): The skill's primary function is to process and execute task definitions which include instructions and scripts.
  • Ingestion points: tasks/<task-id>/instruction.md and tasks/<task-id>/task.toml.
  • Boundary markers: None specified in the provided documentation.
  • Capability inventory: Shell command execution via harbor run (which executes test.sh and solve.sh).
  • Sanitization: None specified; the framework is designed to execute scripts as part of the evaluation lifecycle.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 10:54 AM