ClawAudit verdict

smart-model-switching-glm

smart-model-routing-for-zai

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

Receives external input AND executes processes

Task router selecting z.ai GLM model tiers; network_in and process_exec are expected for a routing layer calling AI APIs, matching the stated purpose.

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

60
security
80
transparency
90
maintenance

What it does

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

Capability combination critical

Receives external input AND executes processes โ€” the shape of a command & control channel

LLM05 ยท LLM06 ยท ASI10

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

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