faion-devtools-developer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill exhibits a significant surface for Indirect Prompt Injection (Category 8). It ingests untrusted external data via 'web scraping', 'browser automation', and 'code review' (SKILL.md). It lacks explicit boundary markers or instructions to ignore embedded commands. When combined with its allowed-tools list—specifically Bash, Write, and Edit—it creates a scenario where malicious content in a scraped page or code snippet could potentially execute commands or modify the filesystem.
  • [COMMAND_EXECUTION] (MEDIUM): The skill explicitly includes Bash in its allowed-tools list to facilitate CI/CD pipelines and browser automation (Puppeteer/Playwright). While these are functional requirements, they represent a high-impact capability that can be abused if the agent's instructions are overridden.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 07:04 AM