Caveat verdict
neirong-gongfang
content-forge-chinese
Chinese content transformation skill (articles to podcasts/PPTs/mindmaps) using NotebookLM and Feishu integrations; all described operations match the stated content-processing purpose with no exfiltration or deceptive behavior.
⚠ 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 (7)
Possible hardcoded credential
references/installation-cn.md · code · API_KEY="your_api_key
Recursive delete from root or home — destructive command
references/installation-cn.md · code · rm -rf ~
Pipe to python — executes piped content as Python code
scenarios/01-wechat-to-ima.md · code · | Python
Accesses shell history/config
references/china-network.md · code · ~/.zshrc
HTTP request to bare IP address — common in malicious payloads
references/china-network.md · code · http://127.0.0.1
References sudo — requests elevated privileges
references/installation-cn.md · code · sudo
pip3 install — installs Python packages at runtime
README.md · code · pip3 install
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.