hackthebox Eval
===============

Status: failed
Score: 66/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Permission surface: secrets or environment access, filesystem or document access

Install:
npx skills add transilienceai/communitytools --skill hackthebox

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, filesystem or document access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- SKILL.md is not self-contained; it references external files (workflow.md, spawning-recipes.md, etc.) that are not included in the excerpt, making it incomplete for standalone use.
- Some workflow steps are vague (e.g., 'If necessary, start the machines', 'Max N concurrent agents' without defining N).
- The skill instructs using anti-bot bypass techniques (Cloudflare/Turnstile evasion) which may violate platform ToS, though it appears intended for legitimate access.
- Quality score needs review
- Permission surface needs review: secrets or environment access, filesystem or document access
- Permission surface: secrets or environment access, filesystem or document access

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- SKILL.md is not self-contained; it references external files (workflow.md, spawning-recipes.md, etc.) that are not included in the excerpt, making it incomplete for standalone use.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- Some workflow steps are vague (e.g., 'If necessary, start the machines', 'Max N concurrent agents' without defining N).
- The skill instructs using anti-bot bypass techniques (Cloudflare/Turnstile evasion) which may violate platform ToS, though it appears intended for legitimate access.

URLs:
- Skill: https://www.openagentskill.com/skills/transilienceai-hackthebox
- Audit: https://www.openagentskill.com/skills/transilienceai-hackthebox/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=transilienceai-hackthebox