Security audit

Sentinel Transaction Safety

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed transaction-checking service, but it tells agents to make autonomous USDC payments without clear local spending limits, so users should review it before use.

Use this only with a dedicated low-balance Base USDC wallet and enforce local per-call, session, daily, and retry budgets. Validate the HTTPS origin, Base network, USDC contract, expected payTo address, quoted tier, nonce, and authorization expiry before signing. Do not use it for sensitive calldata that cannot be sent to a third-party service or from a main wallet with substantial funds.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:76
Finding: Unbounded Server-Directed Autonomous USDC Payment Authorization
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (1)

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The manifest names this skill 'sentinel-transaction-safety' and describes it as a pre-execution transaction safety check, but the file also documents a distinct /v1/attestation counterparty-scoring capability on the same service. While it clarifies that this skill focuses on /v1/guard, embedding the second capability in the skill file expands the apparent scope beyond the manifest's single-purpose description.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.