ClawAudit verdict

xhs-auto

xhsauto

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Xiaohongshu automated publishing workflow generating content locally and using xhs-kit; transparent user-driven workflow with debug/validation steps.

⚠ 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.

38
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (5)

Pattern match high

Possible hardcoded credential

scripts/xhs-image.sh · prose · downgraded · API_KEY="${GOOGLE_API_KEY:-${GEMINI_API_KEY:-}}

Pattern match medium

References sudo — requests elevated privileges

references/text-to-image.md · prose · downgraded · sudo

Pattern match medium

apt-get install — installs system packages

references/text-to-image.md · prose · downgraded · apt-get install

Pattern match medium

yum install — installs system packages

references/text-to-image.md · prose · downgraded · yum install

Pattern match low

Python os.getenv — reads environment variable

scripts/xhs-image.py · prose · downgraded · os.getenv(

Permissions & capabilities

Requires 5 system binaries. (1 elevated: curl).

agent_memorypackage_install

Is this flag fair?

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