editorial-portrait-composition-by-1f0mjj8
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection through its ingestion of untrusted user data.
- Ingestion points: The skill requests 'Intended subject, audience, and use', 'Required references', and 'brand assets' from the user in
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters to isolate user-provided text from the agent's internal logic, nor instructions to ignore embedded commands within user inputs.
- Capability inventory: The skill uses image generation prompts as artifacts, which could be manipulated to include harmful descriptions or override constraints if the user input contains adversarial instructions.
- Sanitization: There is no evidence of input validation, escaping, or filtering for the user-provided 'subject', 'copy', or 'brand' strings before they are interpolated into the 'Preserve / Replace / Avoid' reference contract and the final generation prompt.
Audit Metadata