Caveat verdict

dream-journey

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

Travel planning skill using the flyai-cli for real-time flight/hotel searches; booking is handled via redirect to the official Fliggy platform with no payment data stored or transmitted by the skill itself.

⚠ 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
90
transparency
70
maintenance

Findings (6)

Pattern match critical

Command substitution with curl — remote code execution

references/INSTALL.md · code · bash -c "$(curl

Pattern match high

References sudo — requests elevated privileges

references/INSTALL.md · code · sudo

Pattern match high

apt-get install — installs system packages

references/INSTALL.md · code · apt-get install

Pattern match high

<script> tag in markdown — potential code injection

scripts/generate-dream-prompt.js · prose · downgraded · <script>

Pattern match medium

Instructs covert action — may act without user awareness

README.md · prose · downgraded · silently

Pattern match medium

Accesses shell history/config

references/INSTALL.md · prose · downgraded · ~/.zshrc

Why the tier is capped

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

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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