Verify Claim
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill uses a disclosed external service to verify public factual claims; avoid using it with private or internal information.
This skill appears purpose-aligned and instruction-only. Before installing, understand that claims may be sent to verify.agentutil.net or an optional MCP server for checking, so keep sensitive, private, or internal facts out of it.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Factual claims submitted for verification may be transmitted to the service, which is expected for this skill but could expose sensitive text if used on private/internal claims.
The skill sends claim text to an external verification service as part of its normal workflow.
curl -X POST https://verify.agentutil.net/v1/verify ... -d '{"claim": "The USD to EUR exchange rate is 0.92"}'Use it only for public or non-sensitive facts, consistent with the skill’s own instruction not to use it for private/internal data.
If you separately enable the MCP package, that package’s code and permissions are outside this instruction-only artifact.
The skill references an optional external MCP package, but the provided artifacts include no package code, version pin, or install spec.
MCP server: `@agentutil/verify-mcp` (npm)
Review and pin the MCP package before enabling it, or use the documented HTTPS endpoint without installing extra components.