Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security checks across malware telemetry and agentic risk
This is a coherent lazy-loading template and local recommendation helper with no evidence of hidden data access or unsafe automation.
Reasonable to install if you want lazy skill loading. Review the AGENTS.md changes before merging them, keep SKILLS.md limited to trusted skill paths, and treat the helper’s keyword recommendations as advisory rather than authoritative.
# SKILLS — Available Skills Catalog <!-- This is your agent's skill index. Load this file at session start (it's lightweight). Load individual SKILL.md files only when a task actually needs them. Part of: OpenClaw Skill Lazy Loader (clawhub install openclaw-skill-lazy-loader)
cp ~/.openclaw/skills/openclaw-skill-lazy-loader/SKILLS.md.template ~/my-agent/SKILLS.md cp ~/.openclaw/skills/openclaw-skill-lazy-loader/AGENTS.md.template ~/my-agent/AGENTS.lazy.md # 3. Edit SKILLS.md — fill in your actual skills # 4. Merge AGENTS.lazy.md into your AGENTS.md # 5. Test with context_optimizer.py python3 ~/.openclaw/skills/openclaw-skill-lazy-loader/context_optimizer.py recommend "your next task"
65/65 vendors flagged this skill as clean.