ClawAudit verdict

ghost-cms-skill

ghost-cms

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

Ghost CMS admin integration using GHOST_ADMIN_KEY and GHOST_API_URL from env; warns about broad access and includes security best practices.

⚠ 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.

5
security
70
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match critical

<script> tag in markdown — potential code injection

references/lexical-cards.md · code · <script

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/setup.md · code · http://192.168.1.100

Pattern match medium

Accesses shell history/config

SKILL.md · prose · downgraded · ~/.zshrc

Pattern match medium

Dynamic import() — loads module at runtime

scripts/lexical-builder.js · prose · downgraded · import('

Pattern match medium

Instructs covert action — may act without user awareness

snippets/snippet-config.js · prose · downgraded · silently

Pattern match low

Accesses sensitive environment variables

scripts/snippet-extractor.js · prose · downgraded · process.env.GHOST_ADMIN_KEY

Pattern match low

Popular HTTP library — network access

scripts/update-teapot.js · prose · downgraded · got

Permissions & capabilities

Requires 2 environment variables. Requires 2 system binaries. (1 elevated: npm).

package_install

Is this flag fair?

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