SettlementWitness
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent and low risk, but users should notice that structured task data and optional agent identifiers may be sent to an external verifier for receipts and reputation scoring.
This appears safe to install as an instruction-only skill. Before using it, make sure task specs and outputs do not contain secrets, private customer data, internal business details, or anything you would not want sent to the disclosed external verifier.
Findings (2)
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.
Task specifications and outputs submitted for verification could be visible to the external verifier.
The skill discloses that verification uses an external endpoint, meaning structured task data may be transmitted outside the local environment.
Endpoints https://defaultverifier.com/settlement-witness
Only submit minimal non-sensitive structured data, as the skill itself recommends.
If enabled, verification outcomes may affect an agent's reputation history.
The optional scoring feature suggests task outcomes may be used for reputation or attribution over time.
optional TrustScore update
Use the optional TrustScore feature only when you are comfortable linking outcomes to the supplied agent identity.