bundle-optimizer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill is designed to analyze external React code and has the capability to modify the filesystem through Write and Edit tools. This creates a high-risk surface where malicious instructions embedded in source code (e.g., in comments or string literals) could manipulate the agent into performing unauthorized code changes.\n
  • Ingestion points: Processes external files via Read, Grep, and Glob (defined in SKILL.md).\n
  • Boundary markers: Absent. There are no instructions or delimiters provided to distinguish between data being analyzed and instructions to the agent.\n
  • Capability inventory: Includes Write, Edit, Read, Grep, and Glob permissions.\n
  • Sanitization: No sanitization or validation logic is present to filter malicious content within processed files.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:44 PM