mode-debug

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill creates a direct attack surface by instructing the agent to ingest and act upon untrusted external data.
  • Ingestion points: The 'Required Questions' section explicitly requests 'Exact error message? (Copy verbatim)' and 'logs' from the user.
  • Boundary markers: There are no instructions to use delimiters or ignore embedded prompts within the ingested logs or error messages.
  • Capability inventory: As a debugging and bug-fixing skill, the agent is expected to propose and potentially apply code changes, making it a high-value target for injection-based hijacking.
  • Sanitization: The skill lacks any requirement for the agent to validate or sanitize external input before it is used to influence the agent's reasoning or actions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 11:34 AM