Caveat verdict
zhihu-automation
zhihu-auto-skill
Zhihu automation skill using Playwright browser automation and HTTP API for content publishing and interaction; capabilities match the stated social-media automation purpose with no exfiltration patterns.
⚠ 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.
Permission integrity
package_install
Findings (10)
Possible hardcoded credential
day3-check.js · prose · downgraded · Token='liu-bo-94-4
Accesses shell history/config
SECURITY.md · code · ~/.zshrc
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python
Uses eval() — can execute arbitrary code
zhihu-dump-page.js · prose · downgraded · eval(
Reads files from sensitive system paths
post-day3.js · prose · downgraded · readFileSync('/Users
References child_process — can spawn system processes
scripts/zhihu-bridge.js · prose · downgraded · child_process
Dynamic import() — loads module at runtime
scripts/zhihu-browser.js · prose · downgraded · import('
setuid — privilege escalation mechanism
scripts/zhihu-core.js · prose · downgraded · setuid
Accesses sensitive environment variables
day3-check.js · prose · downgraded · process.env.ZHIHU_COOKIE_KEY
Python os.environ.get — reads environment variable
scripts/python/zhihu_bot.py · prose · downgraded · os.environ.get(
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.