Caveat verdict

agent-desktop

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

The agent-desktop skill enables desktop automation via native OS accessibility trees. It provides a range of commands for interacting with desktop applications, which aligns with its stated purpose. The capability to install packages is used legitimately for its functionality.

⚠ 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.

83
security
70
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match medium

Instructs covert action — may act without user awareness

references/commands-system.md · prose · downgraded · silently

Pattern match low

Base64 encoding/decoding

references/commands-observation.md · prose · downgraded · base64-encode

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