think-aloud-script-generator

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No network operations, file system access, or credential management were detected within the skill's instructions or metadata.
  • [PROMPT_INJECTION]: The skill incorporates untrusted user data into its prompt through template variables such as {{task_to_model}} and {{subject_area}} without explicit boundary markers. This constitutes a surface for indirect prompt injection.
  • Ingestion points: Input variables in the prompt section of SKILL.md.
  • Boundary markers: Absent; user-provided text is interpolated directly into the instruction block.
  • Capability inventory: Limited to text generation; the skill does not define any allowed-tools or subprocess execution capabilities.
  • Sanitization: No input sanitization or schema validation (beyond type) is present to filter potentially malicious instructions in user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM