ClawHub
Back to skill

Security audit

customer-complaint-escalation

Security checks for vulnerabilities and agentic risk

Overview

The skill performs limited local complaint reporting with clear human approval boundaries, although its automation is incomplete.

Expect a duplicate report rather than a completed escalation plan. Remove the template's two leading comment lines before use, since the CSV reader otherwise misreads the header. Review results and legal deadlines, protect reports containing customer details, and assess the optional Windows app separately.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Duplicate detection could support repeat-issue flagging, but the supplied code implements only a duplicate report, not the declared escalation workflow. The static guardrails do not establish approval rules, deadlines, or review-request limits. Local input reading and report writing are consistent supporting operations; the mismatch concerns the materially different primary behavior, not suspicious resource access.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: 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 module claims to merge duplicate complaint records, but only produces a duplicate report.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

L004 explicitly promises to find and merge duplicate records. However, L090–L104 only classify rows and write duplicates.md; the unique rows are never exported, duplicate record fields are never combined, and the source data remains unchanged. Users relying on the documented merge behavior would still have an unmerged complaint log.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.