ctf-malware Eval
================

Status: failed
Score: 69/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Agent safety gate: This skill should not be selected by an agent without explicit human security review.

Install:
npx skills add ljagiello/ctf-skills --skill ctf-malware

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
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Dynamic analysis commands execute potentially malicious binaries; SKILL.md mentions sandboxing but does not provide concrete isolation setup, which could lead to unsafe execution.
- The SKILL.md is a quick reference and relies heavily on supporting files for full workflows; the main file alone is less self-contained for an agent without those files.
- Tool installation commands use pip/apt without integrity verification, though the listed tools are well-known and legitimate.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution

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
- Dynamic analysis commands execute potentially malicious binaries; SKILL.md mentions sandboxing but does not provide concrete isolation setup, which could lead to unsafe execution.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- The SKILL.md is a quick reference and relies heavily on supporting files for full workflows; the main file alone is less self-contained for an agent without those files.

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