fullstack-testing

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill possesses a high-risk surface for indirect prompt injection due to its core function of reading source files and generating output files.
  • Ingestion points: The 'target' parameter allows the agent to ingest the content of local source files (e.g., source code to be tested).
  • Boundary markers: The skill definition does not include delimiters or specific instructions to isolate the model from instructions potentially embedded in the source code.
  • Capability inventory: The skill returns structured file paths and content which an agent would typically write to the filesystem, creating a potential path for unauthorized file modification or creation.
  • Sanitization: No input validation or sanitization of the source code content is performed prior to processing.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 11:10 AM