erroneous-example-designer

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where user-provided input is interpolated into the instructions.
  • Ingestion points: The problem_domain and target_errors fields from the SKILL.md input schema are directly inserted into the model prompt.
  • Boundary markers: There are no delimiters (e.g., triple quotes or xml-like tags) or 'ignore embedded instructions' warnings surrounding the user-provided variables.
  • Capability inventory: Analysis of the skill body and metadata reveals no dangerous capabilities; the skill does not perform network operations, file system writes, or subprocess execution.
  • Sanitization: There is no evidence of input validation, filtering, or sanitization of the external content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM