Back to skill

Security audit

contact-sourcing

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports an unpinned `npx skills` command that could install and run a changing CLI release; part of the scan was incomplete.

Consider postponing installation until the CLI version and dependency are pinned to reviewed versions and the incomplete scan is resolved. The scan inspected 6 of 8 components fully, with 2 partially inspected, so the evidence does not establish that the skill is safe.

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 (3)

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 177)May include surrounding context.

md
- **Resolve before sourcing.** `infra/index.ts` gates every search on a valid,

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

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 skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The command invokes an unpinned npm CLI through npx; it is not an MCP server reference, but the underlying supply-chain concern is valid. If the package is absent locally, installation can retrieve and execute a changing release with the agent process's filesystem and credential access. The legitimate dependency-installation purpose and other approval checkpoints do not ensure the integrity of that executable or the downloaded skill.

Content

No source excerpt is available for this finding.