Back to skill

Security audit

meme-maker

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report that caption text and Imgflip credentials may be sent to a hosted service without a clear privacy notice, and its tool scope is undeclared.

Consider the privacy implications before installing, especially if you might use confidential captions or Imgflip credentials. Scanning was partial: only 2 of 5 components were fully inspected, 3 were partially inspected, and tool-misuse analysis was degraded, 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

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

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.

Hosted meme generation lacks a warning that user-provided captions are sent to Imgflip.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The documentation names Imgflip but does not explicitly explain that caption text leaves the local environment and becomes part of a hosted image. This is a privacy-transparency gap: users could include confidential material without understanding the disclosure, particularly because the skill description also advertises local generation.

Content

No source excerpt is available for this finding.

Meme generation silently sends caption text and credentials to a third-party service.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The function unconditionally sends caption text and supplied or environment-derived Imgflip credentials to Imgflip without a visible privacy or consent boundary. This is a potential unintended disclosure of sensitive captions, not evidence of malicious credential exfiltration: the fixed HTTPS endpoint and Imgflip-specific credentials are consistent with legitimate API authentication.

Content

No source excerpt is available for this finding.