ClawAudit verdict

qxbent

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Comprehensive Qixin enterprise-data query skill; explicitly warns users to configure the token via environment variable rather than in chat, restricts API calls to the documented qixin.com endpoint, and behavior matches 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.

security

transparency

maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="your_token_here

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.zshrc

Pattern match medium

Popular HTTP library — network access

SKILL.md · frontmatter · axios

Pattern match low

Accesses sensitive environment variables

src/client.ts · prose · downgraded · process.env.QXBENT_API_TOKEN

Why the tier is capped

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

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: QXBENT_API_TOKEN). Requires 2 system binaries. (1 elevated: npm).

file_writepackage_install

Is this flag fair?

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