Caveat verdict

agent-spawner

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill explicitly reads ~/.openclaw/.env, env vars matching API_KEY/TOKEN, and all plugin/skill configs, then carries them over to a newly spawned Docker agent — broad credential harvesting and propagation that goes beyond typical deployment tooling and warrants scrutiny.

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

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

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

SKILL.md · code · curl -fsSL https://openclaw.ai/install.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

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

No declared permissions — minimal attack surface.

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