Back to skill

Security audit

TweetClaw

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with medium confidence: most checks were acceptable, though they flagged a possible mismatch between the skill’s stated Twitter/X purpose and a local security-scanning operation.

The verdict is benign, but confidence is medium. Consider whether the reported local security-scanning operation fits your intended use. Skillspector inspected all four listed components, but its analysis was marked partial because two local path-like references could not be resolved; treat the evidence as 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs a security scan of a local skill directory. It does not implement any declared Twitter/X functionality, and security auditing is not described as part of the skill's purpose. The mismatch is the scan itself, not the supporting use of uvx or a pinned external dependency.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · evals/evals.json (reported line 29)May include surrounding context.

json
"wait for explicit approval"
      ],
      "must_not_include": [
        "post without approval",
        "batch write"
      ]
    },