Back to skill

Security audit

PPT Translator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PPTX translation helper with expected local file conversion behavior, though users should limit it to trusted .pptx files and review output paths.

Install only if you are comfortable letting the skill process local .pptx files with python-pptx and LibreOffice. Use trusted presentations, specify output paths deliberately, and do not rely on it for legacy .ppt files despite the broader activation wording.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to execute shell commands and run local scripts, but the manifest does not declare any tool scope or permissions boundaries. This creates an authorization gap where an agent may invoke shell access more broadly than intended, increasing the risk of unsafe command execution on untrusted PPTX inputs or paths.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill activates for PPT/PPTX files, while the documentation later states that legacy .ppt is not supported. This inconsistency can cause the agent to route unsupported .ppt files into a shell-driven processing flow, leading to failures, unsafe fallback behavior, or accidental invocation of converters on untrusted legacy files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file mixes English metadata with user-facing operational instructions in Chinese, including core principles, usage flow, outputs, and cautions. This effectively forces a specific language for understanding and use of the skill without an explicit opt-in or justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring presents usage and operational notes only in Chinese, which imposes a specific language on users without any opt-in or alternative locale. Under the policy, forced language/locale constraints are a natural-language violation unless the skill offers a choice or clearly justifies the locale restriction.

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/translate.py (reported line 65)May include surrounding context.

python
def render_to_png(pptx_path: str, output_dir: str) -> str:
    """Render PPTX to PNG using LibreOffice. Returns PNG path."""
    result = subprocess.run(
        ['libreoffice', '--headless', '--convert-to', 'png',
         '--outdir', output_dir, pptx_path],
        capture_output=True, text=True, timeout=60

Static analysis

No suspicious patterns detected.