Caveat verdict

create-ex

ex-skill

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

This skill automatically decrypts WeChat's encrypted local database via wechat_decryptor.py to extract private chat history without explicit per-session user confirmation of the decryption step; accessing encrypted application databases is an elevated-access operation that warrants caution.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

8
security
90
transparency
70
maintenance

Findings (8)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

exes/chu_ge/training_guide.md · code · http://127.0.0.1

Pattern match high

Writes to SKILL.md — self-modifying skill

tools/skill_writer.py · prose · downgraded · SKILL.md").write

Pattern match medium

Long base64 string (100+ chars) — likely obfuscated payload

exes/chu_ge/knowledge/chats/wechat_conversation_examples.txt · prose · downgraded · 30350201010421301f02020106040253480410a7b429e587522e9f55340fa8f55a5c19020301e7ac

Pattern match medium

pip3 install — installs Python packages at runtime

README_EN.md · code · pip3 install

Pattern match medium

Accesses system credential store

tools/wechat_decryptor.py · prose · downgraded · Keychain

Pattern match medium

Uses exec() — may execute shell commands

tools/wechat_decryptor.py · prose · downgraded · exec(

Pattern match medium

subprocess execution — runs system commands from Python

tools/wechat_decryptor.py · prose · downgraded · subprocess.run(

Pattern match low

Python shutil file operation — copies/moves/deletes files

tools/version_manager.py · prose · downgraded · shutil.rmtree(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API