Back to skill

Security audit

bike-theft-shield

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this bike security and theft-response skill benign with high confidence; the findings point to limited scope and privacy concerns, not reported malicious behavior.

The verdict is benign, but consider whether you want the undeclared used-bike check and review what personal information you share through external registries or community posts. The scanner completed coverage of all five components, though the reported file-writing capability's runtime permissions were not verified.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The first three workflows align with the description. The fourth adds a distinct user-facing used-bike purchase check, rather than a supporting implementation detail of the declared workflows. This is a limited scope mismatch, not evidence of malicious behavior. The supplied chunk contains command invocations only, so the underlying implementation and any resource access cannot be verified.

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 recovery workflow instructs sharing bike information through third-party registries and community posts without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

These steps instruct users to flag the bike on external registries and publish its registry link in community groups, rather than merely listing available services. The skill does not warn that registry details and linked posts may be publicly accessible or advise users to exclude private ownership documents, contact information, and precise home locations.

Content

No source excerpt is available for this finding.