ClawHub
Back to skill

Security audit

AssetFare Route Quote

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto route quoting and unsigned action-preparation guide with strong user-approval boundaries and no bundled executable code.

Install only if you intend to use AssetFare for crypto route comparison or caller-approved unsigned bridge plans. Treat it as financial workflow guidance: verify every quote, fee, address, chain, amount, deadline, payload hash, and unsigned action in your own wallet before signing, and never provide private keys or seed phrases.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest and top-level description present the skill as quote-only and non-executing, but the body includes prepare/session execution workflows, approval handling, wallet requirements, and session-token mechanics. This mismatch can cause an agent or reviewer to grant the skill broader trust than warranted, increasing the chance of unintended progression from read-only quoting into transaction preparation workflows.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md
3. Compare the result with other executable routes at the intended amount.
4. Require caller approval before `assetfare_start_wallet_auth`, session creation, or action preparation.
5. The wallet owner signs only the exact non-transactional login message.
6. Keep the returned access token out of source, logs, issues, and transcripts.
7. Verify every `agent_must_verify` item before the caller signs an unsigned action.

After any delay or error, read the workflow state and current asset location. Never guess, silently rebuild, or resend a stale action.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
# AssetFare Route

Use REST/OpenAPI v2 at `https://api.assetfare.dev/v2/openapi.json` as the primary interface. The optional MCP endpoint is `https://api.assetfare.dev/mcp`.

## When to request an AssetFare quote

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document states that a quote grants no authority for action preparation, but later provides concrete prepare/session execution steps. Even if the later steps require explicit approval, the contradictory guidance can confuse an agent into treating the skill as safer or more limited than it really is, weakening policy enforcement around transaction-related actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.