OpenClaw Session Model Switcher

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

When invoked, the agent may switch the current session to a different model or provider.

Why it was flagged

This gives the skill authority to change the active model for the current session. That behavior is the stated purpose and is bounded to the current session, but users should understand it changes the agent's runtime behavior.

Skill content
directly execute `/model <provider/model>` in the current session after resolving a unique target
Recommendation

Use the skill only when you intend to change the current session model, and review ambiguous choices before selecting one.

What this means

The actual model resolution behavior may depend on local helper scripts outside the reviewed package.

Why it was flagged

The handler makes and runs helper scripts from a workspace scripts directory, but those helper scripts are not included in the provided file manifest and are not declared as required paths. This creates a provenance/packaging item users should verify.

Skill content
SWITCH_SCRIPT="$WORKSPACE_DIR/scripts/switch-model.sh" ... chmod +x "$SWITCH_SCRIPT" "$STATUS_SCRIPT" "$LIST_SCRIPT" ... RESOLUTION="$($SWITCH_SCRIPT "$SELECTION")"
Recommendation

Before installing or using it, verify that scripts/switch-model.sh, scripts/list-models.sh, and scripts/model-status.sh are trusted and only perform the documented model-listing/status/switch-resolution tasks.