Caveat verdict

directus_io

directus-io

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Reference documentation skill for the Directus open-source headless CMS; directs the agent to read local reference files before answering — no execution or credential access.

⚠ 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.

0
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · SECRET: 'your-random-secret

Pattern match high

References sudo — requests elevated privileges

references/troubleshooting.md · code · sudo

Pattern match high

Dynamic import() — loads module at runtime

references/typescript-patterns.md · code · import('

Pattern match medium

Changes file ownership

references/troubleshooting.md · code · chown

Pattern match medium

Instructs covert action — may act without user awareness

references/troubleshooting.md · prose · downgraded · silently

Pattern match medium

Accesses sensitive environment variables

references/typescript-patterns.md · code · process.env.DIRECTUS_TOKEN

Pattern match low

Makes HTTP request to external URL

references/data-modeling.md · code · fetch('https://

Pattern match low

Opens WebSocket connection

references/sdk-and-api.md · prose · downgraded · WebSocket

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

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