Caveat verdict

desktop-agent-ops

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

A well-structured desktop GUI automation guide with an explicit step-by-step loop, window-scoped targeting, and verification gates; executionSinkDetected is expected for a skill that orchestrates Python scripts for screenshots and input actions.

⚠ 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.

15
security
100
transparency
90
maintenance

Findings (8)

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

scripts/first_run_setup.py · prose · downgraded · curl -LsSf https://astral.sh/uv/install.sh | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/first_run_setup.py · prose · downgraded · | sh

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

subprocess execution — runs system commands from Python

scripts/bootstrap_env.py · prose · downgraded · subprocess.run(

Pattern match medium

References sudo — requests elevated privileges

scripts/first_run_setup.py · prose · downgraded · sudo

Pattern match medium

Downloads executables from external URLs

scripts/first_run_setup.py · prose · downgraded · download from https://

Pattern match low

Python os.environ.get — reads environment variable

scripts/bootstrap_env.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/cleanup_task.py · prose · downgraded · shutil.rmtree(

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

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