Trusted — Risk Score 5/100
Last scan:21 hr ago Rescan
5 /100
council-v2
Multi-model council review skill that dispatches 3-5 independent AI reviewers and applies mechanical synthesis
This is a legitimate multi-model code review orchestration skill with transparent, documented behavior and no malicious indicators.
Skill Namecouncil-v2
Duration23.4s
Enginepi
Safe to install
This skill is safe to use. No security concerns identified.
ResourceDeclaredInferredStatusEvidence
Filesystem READ READ ✓ Aligned SKILL.md states 'Reads content from file or stdin'
Shell WRITE WRITE ✓ Aligned SKILL.md declares bash script execution for council.sh and synthesize.py
Network NONE NONE No network calls found in scripts; external URLs in README are documentation onl…
Environment NONE NONE No environment variable access observed
Skill Invoke WRITE WRITE ✓ Aligned SKILL.md explicitly states 'spawns 3-5 independent AI reviewers'
4 findings
🔗
Medium External URL 外部 URL
https://openrouter.ai
README.md:43
🔗
Medium External URL 外部 URL
https://openrouter.ai/api/v1
README.md:48
🔗
Medium External URL 外部 URL
https://docs.openclaw.ai/concepts/models
README.md:57
🔗
Medium External URL 外部 URL
http://json-schema.org/draft-07/schema#
references/schema.md:7

File Tree

10 files · 35.0 KB · 1152 lines
Markdown 7f · 780L Python 1f · 202L Shell 2f · 170L
├─ 📁 assets
│ └─ 📝 council-v2-banner.md Markdown 9L · 349 B
├─ 📁 references
│ ├─ 📝 review-types.md Markdown 97L · 1.9 KB
│ ├─ 📝 role-prompts.md Markdown 140L · 4.4 KB
│ ├─ 📝 schema.md Markdown 149L · 3.7 KB
│ └─ 📝 synthesis-rules.md Markdown 92L · 2.7 KB
├─ 📁 scripts
│ ├─ 🔧 council.sh Shell 130L · 3.0 KB
│ ├─ 🔧 retro.sh Shell 40L · 932 B
│ └─ 🐍 synthesize.py Python 202L · 6.6 KB
├─ 📝 README.md Markdown 98L · 3.9 KB
└─ 📝 SKILL.md Markdown 195L · 7.6 KB

Security Positives

✓ Comprehensive SKILL.md with clear behavior documentation
✓ No credential harvesting or sensitive data access
✓ No obfuscation techniques (base64, eval, etc.)
✓ No remote script execution patterns (curl|bash, wget|sh)
✓ Clean subprocess usage limited to documented orchestration tasks
✓ JSON validation in synthesize.py prevents malformed input exploits
✓ No supply chain risks - Python stdlib only, no external dependencies
✓ Set -euo pipefail in bash scripts prevents silent failures
✓ No hidden functionality - all behavior matches documentation