Back to skill

Security audit

goal-coverage

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it found an unpinned command that can download and run a package, while some referenced content was only partly inspected.

The verdict is suspicious, so consider holding off on installation until the package-running command is pinned to a reviewed version and the partially inspected content is checked. The scan covered 10 of 11 components, so the available evidence is incomplete; suspicious does not mean the author is malicious.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
4. **Check, then plan.** `node --import tsx evals/contract.mjs` from this skill's folder, then

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
- `node --import tsx evals/contract.mjs` passes: a `claudeCode` harness bound to an Anthropic

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx --yes @cargo-ai/cli'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

Although this is a CLI rather than an MCP server, the fallback npx --yes @cargo-ai/cli downloads and executes an unpinned package without an approval prompt. A compromised or malicious future release could execute with the agent sandbox's repository access and available credentials; the viewer role limits Cargo API operations but does not prevent arbitrary package code execution.

Content

No source excerpt is available for this finding.