ClawHub
Back to skill

Security audit

Poetry Recitation

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it advertises, but it needs Review because it can use cloned voices without a confirmation step and can write output videos to unrestricted file paths.

Install only if you are comfortable with a skill that may use an existing cloned voice automatically for poem recitations. Avoid supplying arbitrary --output paths, and prefer running it in a workspace where accidental file overwrites are contained. Review voice choice, poem text, and output path before sharing generated videos.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/poetry_recitation.py:219
Finding

Unrestricted Output Path Allows Overwriting Arbitrary Writable Files

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill declares shell and file-read-like behavior in its documented workflow but does not scope or constrain those capabilities with explicit permissions or allowed tools. This increases the blast radius of prompt-injection or operator misuse, because a caller can trigger local command execution and access local paths such as the TTS pipeline and output directories without any declared guardrails.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description states the skill generates recitation videos with Chinese subtitles, and the rest of the document does not indicate any user opt-in or language selection. This is a natural-language locale policy concern because the skill appears to force a specific output language by default.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow says to send generated media to the user with no extra confirmation even though the skill supports cloned-voice generation and creates files for delivery. That removes an important consent and review checkpoint for a sensitive output type, increasing the risk of impersonation, misuse of a cloned voice, or accidental delivery of harmful or unauthorized content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file includes usage examples, CLI defaults, and runtime messages exclusively in Chinese, which imposes a specific language/locale on users. The file does not offer a language option or explain that the skill is intentionally limited to a Chinese-speaking or region-specific context.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/poetry_recitation.py (reported line 138)May include surrounding context.

python
"--model", model,
        "--output", output_audio_path,
    ]
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"❌ TTS 合成失败: {result.stderr}", file=sys.stderr)
        sys.exit(1)

Static analysis

No suspicious patterns detected.