ClawAudit verdict

macmini-knowledge-base

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Installs packages AND executes processes

Sets up a local RAG knowledge base using Ollama and local embedding models; all data stays local, the Feishu integration is for sending summaries to the user's own account, matching the stated purpose.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
70
transparency
90
maintenance

What it does

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

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match high

subprocess execution — runs system commands from Python

SKILL.md · code · subprocess.run(

Pattern match medium

pip3 install — installs Python packages at runtime

SKILL.md · code · pip3 install

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

os.system/popen — direct OS command execution

scripts/utils.py · prose · downgraded · os.system(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

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