Caveat verdict

chinese-toolkit

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Chinese NLP toolkit installing standard Python packages (jieba, pypinyin, paddlepaddle) and integrating translation APIs (Baidu, Google, Tencent) with trial quotas; capabilities match the stated text/speech processing purpose.

⚠ 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.

0
security
40
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Pattern match high

apt-get install — installs system packages

SKILL.md · code · apt-get install

Pattern match high

References SSH/GPG private keys

GITHUB_RELEASE_GUIDE.md · code · ssh-key

Pattern match high

Accesses .ssh directory

GITHUB_RELEASE_GUIDE.md · code · .ssh/

Pattern match high

Uses exec() — may execute shell commands

references/doc-search.md · code · exec(

Pattern match low

Python os.getenv — reads environment variable

chinese_tools_core.py · prose · downgraded · os.getenv(

Pattern match low

Contains shortened/invite URL

CLAWHUB_RELEASE_GUIDE.md · code · discord.gg/claw

Pattern match low

pip3 install — installs Python packages at runtime

install.sh · prose · downgraded · pip3 install

Why the tier is capped

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

Permissions & capabilities

Requires 2 system binaries. (1 elevated: pip).

credential_accesspackage_install

Is this flag fair?

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