v0.1.0

Uniswap Monitor Tokenjar

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:34 AM.

Analysis

This instruction-only skill appears to monitor Uniswap TokenJar data and does not request credentials, local file access, or burn-execution authority.

GuidanceBefore installing, confirm you trust the source and the Uniswap MCP/subagent environment. Use it for monitoring only, not for executing burns, and set streaming duration or alert thresholds explicitly when requesting live mode.

Findings (3)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

SKILL.md

allowed-tools: ... mcp__uniswap__subscribe_tokenjar ... mcp__uniswap__get_token_price

The skill can call live subscription and pricing/balance/history tools. These tools are central to the monitoring purpose, and the documented streaming duration is bounded.

User impactWhen invoked, the agent may open a short live TokenJar data stream and make Uniswap data queries.

RecommendationUse streaming only when intended, and specify duration and alert thresholds clearly.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

metadata

Source: unknown; Homepage: none

The registry provenance metadata is limited. The risk is reduced because the artifact is instruction-only and no executable install spec or code files are present.

User impactIt may be harder to verify the publisher or canonical source before installation.

RecommendationInstall only from a trusted registry or reviewed repository path, and confirm the skill contents match what you expect.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityInfoConfidenceHighStatusNote

SKILL.md

Delegate to `Task(subagent_type:protocol-fee-seeker)` in monitoring mode

The dashboard computation is delegated to another agent context. This is disclosed and appears limited to TokenJar analysis data, but users should notice the inter-agent delegation.

User impactProtocol data and the analysis prompt may be passed to the named subagent for dashboard generation.

RecommendationEnsure the protocol-fee-seeker subagent is trusted and constrained to monitoring; do not use this skill for burn execution.