Caveat verdict

AgentYard

agent-marketplace

🟠 Risky

Significant risk patterns flagged — automated deep scan, not behavioral proof.

AgentYard enables agents to hire other agents and make real Lightning Network payments with no middleman or manual approval per transaction, creating real financial exposure without explicit per-hire user confirmation.

⚠ 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.

security

transparency

maintenance

Findings (8)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-key-here

Pattern match critical

Pipe to bash — executes piped content as shell commands

SETUP.md · code · | bash

Pattern match critical

Recursive delete from root or home — destructive command

SETUP.md · code · rm -rf ~

Pattern match high

References sudo — requests elevated privileges

SETUP.md · code · sudo

Pattern match high

Downloads executables from external URLs

SETUP.md · code · Download from https://

Pattern match high

apt-get install — installs system packages

SETUP.md · code · apt-get install

Pattern match low

Popular HTTP library — network access

lib/api.sh · prose · downgraded · got

Pattern match low

References agent configuration files

lib/api.sh · prose · downgraded · agent_config

Why the tier is capped

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

Permissions & capabilities

Requires 2 system binaries. (1 elevated: curl).

network_in

Is this flag fair?

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