Back to skill

Security audit

Chat Human

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because Skillspector found a high-confidence instruction-priority weakness; the scan was otherwise largely clean, but some references were unresolved.

Consider the review warning before installing. The main concern is unsafe instruction ordering; ask whether it has been corrected, and clarify what file access the skill needs and what permissions the host will enforce. Skillspector inspected all six listed components, but marked its analysis partial because several local references could not be resolved, so the evidence is incomplete.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

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

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.

The composition contract places current-turn user instructions above the system prompt.

Medium
Category
Prompt Injection
Confidence
94% confidence
Finding

The composition table explicitly assigns current-turn user instructions higher priority than the system prompt, creating an instruction-hierarchy inversion that could encourage an agent to disregard higher-priority constraints. Its focus on persona and presentation limits the apparent intended scope, but labeling user instructions as highest priority and grouping system prompts with ordinary persona files makes the boundary unsafe.

Content

No source excerpt is available for this finding.