Caveat verdict
create-ex
ex-skill
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.
Findings (8)
HTTP request to bare IP address — common in malicious payloads
exes/chu_ge/training_guide.md · code · http://127.0.0.1
Writes to SKILL.md — self-modifying skill
tools/skill_writer.py · prose · downgraded · SKILL.md").write
Long base64 string (100+ chars) — likely obfuscated payload
exes/chu_ge/knowledge/chats/wechat_conversation_examples.txt · prose · downgraded · 30350201010421301f02020106040253480410a7b429e587522e9f55340fa8f55a5c19020301e7ac
pip3 install — installs Python packages at runtime
README_EN.md · code · pip3 install
Accesses system credential store
tools/wechat_decryptor.py · prose · downgraded · Keychain
Uses exec() — may execute shell commands
tools/wechat_decryptor.py · prose · downgraded · exec(
subprocess execution — runs system commands from Python
tools/wechat_decryptor.py · prose · downgraded · subprocess.run(
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?
Thanks — recorded.