Trusted — Risk Score 5/100
Last scan:1 day ago Rescan
5 /100
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve
This is a legitimate documentation/methodology skill providing proactive agent patterns with comprehensive security hardening practices. No malicious behavior detected.
Skill Nameproactive-agent
Duration34.2s
Enginepi
Safe to install
This skill is safe to use. The security audit script and documented security practices are well-designed. Continue using as-is.
ResourceDeclaredInferredStatusEvidence
Filesystem NONE READ ✓ Aligned Documentation-only skill, no file operations required
Network NONE NONE No network operations in implementation
Shell NONE NONE Audit script is for user execution only, not auto-run
Environment NONE NONE No environment variable access
Skill Invoke NONE NONE No skill invocation patterns
Clipboard NONE NONE No clipboard access
Browser NONE NONE No browser operations
Database NONE NONE No database operations
3 findings
🔗
Medium External URL 外部 URL
https://x.com/halthelobster
SKILL-v2.3-backup.md:526
🔗
Medium External URL 外部 URL
https://clawdhub.com/halthelobster/bulletproof-memory
SKILL-v2.3-backup.md:550
🔗
Medium External URL 外部 URL
https://clawdhub.com/halthelobster/para-second-brain
SKILL-v2.3-backup.md:550

File Tree

14 files · 80.9 KB · 2670 lines
Markdown 12f · 2516L Shell 1f · 149L JSON 1f · 5L
├─ 📁 assets
│ ├─ 📝 AGENTS.md Markdown 155L · 3.8 KB
│ ├─ 📝 HEARTBEAT.md Markdown 128L · 2.9 KB
│ ├─ 📝 MEMORY.md Markdown 47L · 836 B
│ ├─ 📝 ONBOARDING.md Markdown 103L · 2.4 KB
│ ├─ 📝 SOUL.md Markdown 40L · 1.4 KB
│ ├─ 📝 TOOLS.md Markdown 55L · 1.0 KB
│ └─ 📝 USER.md Markdown 36L · 926 B
├─ 📁 references
│ ├─ 📝 onboarding-flow.md Markdown 158L · 4.0 KB
│ └─ 📝 security-patterns.md Markdown 109L · 3.0 KB
├─ 📁 scripts
│ └─ 🔧 security-audit.sh Shell 149L · 4.0 KB
├─ 📋 _meta.json JSON 5L · 137 B
├─ 📝 SKILL-v2.3-backup.md Markdown 554L · 19.7 KB
├─ 📝 SKILL-v3-draft.md Markdown 499L · 16.6 KB
└─ 📝 SKILL.md Markdown 632L · 20.4 KB

Security Positives

✓ Comprehensive prompt injection defense documented with multiple detection patterns
✓ Security audit script checks credential file permissions (600)
✓ Clear separation between internal actions and external actions requiring approval
✓ External content classification and instruction isolation well-defined
✓ Incident response procedures documented for detected attacks
✓ Skill installation vetting policy to prevent supply chain attacks
✓ Context leakage prevention for shared channels
✓ No dangerous patterns: no base64, no eval, no curl|bash, no credential harvesting
✓ Credential storage in .credentials/ with proper permission guidance
✓ MIT license with clear disclaimer