ClawAudit verdict

s2-matrix-pod

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

The skill assigns a deterministic virtual space to the OpenClaw agent and equips it with a visual face, without any sensitive capabilities.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

100
security
70
transparency
70
maintenance

Findings (1)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("working directory") and emits it outward ("paste"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · To ensure absolute transparency for the OpenClaw sandbox, here is exactly what this script executes: 1. **File Write (Local I/O):** When executed, the Python sc

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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