ai-output-critical-audit-designer

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the ai_output_sample input field.
  • Ingestion points: Untrusted text enters the agent context through the ai_output_sample parameter defined in the input schema.
  • Boundary markers: The prompt template in SKILL.md interpolates the sample directly without using distinct delimiters (such as XML tags or triple quotes) or specific instructions to treat the content as data only.
  • Capability inventory: The skill is restricted to text generation; it does not utilize shell execution, file system modifications, or network tools, which significantly limits the potential impact of a successful injection.
  • Sanitization: No input sanitization or filtering is applied to the user-provided sample text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:53 AM