debugging-code

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing runtime data that could be under attacker control.
  • Ingestion points: Runtime data is ingested via xdebug_get_frame_values, xdebug_get_value_by_path, and xdebug_evaluate_expression (SKILL.md).
  • Boundary markers: There are no instructions for the agent to use boundary markers or delimiters when handling this data (SKILL.md).
  • Capability inventory: The skill provides capabilities to execute project configurations (execute_run_configuration), modify memory (xdebug_set_variable), and execute code in the debugged context (xdebug_evaluate_expression) (SKILL.md).
  • Sanitization: No sanitization of ingested runtime data is required by the instructions (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 12:29 PM
Security Audit — agent-trust-hub — debugging-code