analyzing-android-malware-with-apktool Eval
===========================================

Status: review
Score: 64/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add adriannoes/awesome-agentic-ai --skill analyzing-android-malware-with-apktool

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: Apache-2.0
- WARN Permission surface: shell or command execution, network or browser 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.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Permission surface: shell or command execution, network or browser access
- High-risk permission hints: Shell or command execution
- Financial research output is not financial advice; require human review before any live investment decision
- SKILL.md and metadata emphasize apktool and jadx, but the provided script and workflow only use androguard; there is no actual apktool or jadx integration.
- SKILL.md lacks explicit installation instructions, dependency setup commands, and environment preparation beyond listing prerequisites.
- No safe handling and disposal guidance for malware samples is included, though an isolated analysis environment is mentioned.
- Expected output mentions a JSON report with risk score, but SKILL.md does not define the report schema or how the risk score is calculated.
- Limitations of static analysis, such as obfuscation resistance, packed APKs, or encrypted DEX payloads, are not documented.

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 and metadata emphasize apktool and jadx, but the provided script and workflow only use androguard; there is no actual apktool or jadx integration.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- Financial research output is not financial advice; require human review before any live investment decision
- SKILL.md lacks explicit installation instructions, dependency setup commands, and environment preparation beyond listing prerequisites.
- No safe handling and disposal guidance for malware samples is included, though an isolated analysis environment is mentioned.

URLs:
- Skill: https://www.openagentskill.com/skills/adriannoes-analyzing-android-malware-with-apktool
- Audit: https://www.openagentskill.com/skills/adriannoes-analyzing-android-malware-with-apktool/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=adriannoes-analyzing-android-malware-with-apktool