language-demand-analyser

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates several user-provided input fields directly into the primary prompt without using structural delimiters or instructions to ignore embedded commands, creating a surface for indirect prompt injection.
  • Ingestion points: task_description, student_level, subject_area, language_proficiency, student_profiles, task_materials, and prior_language_instruction fields in SKILL.md.
  • Boundary markers: Absent. Input data is concatenated with bold labels but lacks clear encapsulation such as XML tags or triple quotes.
  • Capability inventory: None. The skill does not have access to tools, network operations, or file system modifications.
  • Sanitization: Absent. There is no evidence of input filtering or validation before the data is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM