Skill Evolver

Use this skill when evolving skills and extracting patterns from execution data. Provides automatic feedback collection, AI suggestion generation, impact tra...

This skill looks like a plausible 'meta' tool, but there are red flags you should resolve before installing: - Ask the author for the missing source code (src/*) that SKILL.md and package.json reference. Without it you can't verify what will run. - Clarify what event stream/logs the skill will access and how: which platform API, file paths, or hooks? The manifest currently declares no credentials or config paths which is inconsistent with its claims. - Confirm exactly what the skill will do with Read/Write/Bash/Exec tools. Request a minimal permission list and explicit commands or endpoints. If it needs shell access, prefer running it in an isolated sandbox/container. - Ask how data is stored/encrypted locally and where keys are kept. If the skill processes sensitive user data, require documented encryption and retention policies (and proof in code). - Do not grant system-level or cloud credentials until you review the implementation. If possible, run the skill in a test account or sandbox first and monitor file/system/network activity. If the author can't provide the missing code or concrete integration details, treat the package as incomplete and avoid installing it on production systems.

Type: OpenClaw Skill Name: skill-evolver-v2 Version: 0.3.0 The skill-evolver bundle describes a 'meta-skill' designed to monitor, analyze, and modify other skills through a 'Hook system' and 'Event-driven architecture.' It requests high-privilege tools (Bash, Exec) and explicitly states it captures inputs and outputs of other skill executions (SKILL.md, CLAWHUB-UPLOAD.md). While the documentation claims data is stored locally, the capability to intercept and record all agent-skill interactions represents a significant surveillance and privacy risk, especially as the core implementation code for the monitoring logic is not provided for review.