ClawAudit verdict
wechat-mp-toolkit
dongrebeccahhh-wechat-mp-toolkit
WeChat public account toolkit for article creation, cover generation, and publishing via the official WeChat API; credentials are stored in a local config file and all operations align with the stated purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (6)
References sudo — requests elevated privileges
SKILL.md · code · sudo
apt-get install — installs system packages
SKILL.md · code · apt-get install
yum install — installs system packages
SKILL.md · code · yum install
Possible hardcoded credential
scripts/full-workflow.js · prose · downgraded · Secret: '3139a3d2a930678209d8ffae5e103005
Popular HTTP library — network access
SKILL.md · code · axios
References child_process — can spawn system processes
scripts/full-workflow.js · prose · downgraded · child_process
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.
package_install Is this flag fair?
Thanks — recorded.