Meta-Cognition Coach
Security checks across malware telemetry and agentic risk
Overview
This appears to be a straightforward local study-coaching tool; the main thing to notice is that it runs a small Python script and saves some reflection or strategy inputs to local log files.
This skill looks benign and purpose-aligned. Before installing or using it, be aware that it runs a local Python script and may leave local reflection or strategy logs containing whatever study details you enter.
VirusTotal
No VirusTotal findings
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill may execute local code from the artifact, but the code appears limited to printing coaching guidance and writing local logs.
The documented usage asks the user to run the included Python helper. This is expected for the skill's CLI-style functionality, and the provided code does not show hidden downloads, shell chaining, or unrelated execution.
python3 scripts/main.py reflect --task "数学作业" --approach "直接做题遇到困难"
Run it only if you are comfortable executing the included Python script; no extra privileges or credentials appear necessary.
Study tasks, approaches, subjects, or difficulties entered into the tool may remain in local log files after use.
The script persistently stores user-provided reflection data locally; the strategy command similarly writes to strategy_log.json. This is purpose-aligned but may retain personal learning details.
with open("reflection_log.json", "a", encoding="utf-8") as f:
f.write(json.dumps(data, ensure_ascii=False) + "\n")Avoid entering highly sensitive personal information, and delete reflection_log.json or strategy_log.json if you do not want the records retained.