vitepress-migration

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill is susceptible to Indirect Prompt Injection through untrusted data ingestion.
  • Ingestion points: The skill processes all Markdown documents within a user-provided <source-dir> during the normalization and cleanup phases (Step 2 and Step 7).
  • Boundary markers: Absent. There are no delimiters or instructions provided to isolate untrusted file content from the agent's logic.
  • Capability inventory: The agent is instructed to execute Python scripts (scripts/detect_issues.py, scripts/cleanup.py) and NPM commands (npm run docs:dev), creating a path for malicious content to influence execution.
  • Sanitization: Absent. No validation or escaping is performed on the documentation content before it is processed by the agent or passed to shell commands.
  • [COMMAND_EXECUTION] (MEDIUM): The skill directs the agent to execute shell commands and local Python scripts. The logic within scripts/detect_issues.py and scripts/cleanup.py is opaque and unverifiable as the script contents were not provided for analysis.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:14 PM