honeybadge/harbor
Framework for AI agent evaluation in containerized environments. Use when: (1) Running agent evaluations with `harbor run` against benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.), (2) Creating custom benchmark tasks with Dockerfile, instruction.md, solution, and tests, (3) Building adapters to convert existing benchmarks to Harbor format, (4) Implementing custom agents extending BaseAgent or BaseInstalledAgent, (5) Scaling evaluations to cloud providers (Daytona, Modal, E2B), (6) Exporting traces for RL/SFT training, (7) Debugging Harbor runs or inspecting package internals.
79
99%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill's core workflow loads external benchmark datasets and task instructions from a registry or user-provided sources (see references/commands.md for "harbor run -d <dataset@version>" and the --registry-url/harbor datasets list), adapters explicitly accept --source-url and load benchmark data from external repos (references/adapters.md), and tasks include instruction.md (references/tasks.md) which the agent reads and acts on—so untrusted, user-generated third‑party content can be ingested and materially influence agent actions.
- Audited
- Security analysis