Caveat verdict

omniscient

linux-omniscient

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

Comprehensive Linux system control skill with broad declared capabilities (hardware, IoT, GPIO, audio, etc.) but all operations are documented legitimate system administration tasks using Python libraries; no exfiltration, injection, or deceptive behavior present.

⚠ 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
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (9)

Pattern match high

apt-get install — installs system packages

SKILL.md · frontmatter · apt-get install

Pattern match high

Pipe to python — executes piped content as Python code

SKILL.md · prose · downgraded · | Python

Pattern match high

Recursive delete from root or home — destructive command

SKILL.md · prose · downgraded · rm -rf /

Pattern match high

HTTP request to bare IP address — common in malicious payloads

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

Pattern match high

Uses eval() — can execute arbitrary code

references/security_checklist.md · prose · downgraded · eval(

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Uses exec() — may execute shell commands

references/security_checklist.md · prose · downgraded · exec(

Pattern match medium

subprocess execution — runs system commands from Python

scripts/bluetooth_controller.py · prose · downgraded · subprocess.check_output(

Pattern match medium

subprocess with shell=True — command injection vector

scripts/common.py · prose · downgraded · subprocess.run( cmd_str, capture_output=True,

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D/E). 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.

package_install

Is this flag fair?

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