ClawAudit verdict

gandi

gandi-skill

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

A Gandi domain registrar management skill with explicit and prominent security warnings about destructive operations; the skill requires user-controlled API tokens and documents all risk vectors clearly including DNS breakage and financial transactions.

⚠ 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.

25
security
60
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="YOUR_PERSONAL_ACCESS_TOKEN

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.zshrc

Pattern match medium

References sudo — requests elevated privileges

references/livedns.md · prose · downgraded · sudo

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · axios

Pattern match low

Accesses sensitive environment variables

scripts/config-helper.js · prose · downgraded · process.env.GANDI_API_TOKEN

Permissions & capabilities

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

file_writepackage_installnetwork_in

Is this flag fair?

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