Back to skill

Security audit

contract-interact-checklist

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a simple smart-contract safety checklist, but its declared tool access is broader than the checklist needs and conflicts with its own no-network/no-filesystem claims.

Review this before installing because the requested agent tools are broader than the actual checklist appears to need. Prefer a version that removes Write and WebFetch unless they are clearly justified, and that aligns the usage docs with the real command-line options.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file imposes a specific language for agent instructions through its natural-language content, but does not provide any opt-in, alternative language, or justification for the locale constraint. Under the stated policy, forcing a language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document presents the title and core description primarily in Chinese, with only a partial English summary, and does not state that users may choose their preferred language. Under the policy, language constraints should be opt-in or clearly justified; here the locale choice appears imposed rather than optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The top-level description shown in the manifest is Chinese-only, which can force a specific language experience on users or systems that rely on this field for discovery and activation context. Although bilingual fields exist elsewhere, this prominent natural-language field does not explicitly offer a user language choice or opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The English usage text states users should pass a target contract address and operation type, and the Chinese section repeats the same claim. However, the manifest's actual input_schema only defines have, approve, and json, with no contract address or operation-type argument, so the documentation actively misstates what the skill interface accepts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The user-facing description and output strings are entirely in Chinese, and the skill does not offer any language or locale selection. Under the policy for natural-language violations, forcing a specific language without user opt-in is reportable unless clearly documented as region-specific, which is not present here.

Content

No source excerpt is available for this finding.