Caveat verdict
universal-agent
The skill explicitly generates arbitrary shell commands or Python scripts and auto-executes them without user review, covering hardware control, CLI tools, and system administration — broad unconstrained execution beyond a specific stated purpose.
⚠ 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.
Permission integrity
credential_access
Findings (10)
Possible hardcoded credential
references/README.md · code · api_key="your-key
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
references/README.md · code · curl -fsSL https://ollama.ai/install.sh | sh
Pipe to sh — executes piped content as shell commands
references/README.md · code · | sh
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Recursive delete from root or home — destructive command
references/README.md · prose · downgraded · rm -rf /
Uses eval() — can execute arbitrary code
scripts/universal_agent.py · prose · downgraded · eval(
subprocess with shell=True — command injection vector
scripts/universal_agent.py · prose · downgraded · subprocess.Popen(
command,
shell=True
Uses exec() — may execute shell commands
scripts/universal_agent.py · prose · downgraded · exec(
Python os.environ.get — reads environment variable
scripts/universal_agent.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/universal_agent.py · prose · downgraded · urllib.request
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
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.