product-photography
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill identifies a surface for indirect prompt injection through its use of un-sanitized placeholders in prompt templates.
- Ingestion points: Untrusted data enters the agent context through placeholders such as
[Product name],[Product],[setting], and[mood]found throughoutSKILL.md. - Boundary markers: There are no delimiters or 'ignore' instructions wrapping the interpolated variables.
- Capability inventory: The skill leverages image generation capabilities (via integration with FAL.ai/Image Generation skills).
- Sanitization: No escaping or validation of external content is specified.
- No Code (SAFE): The skill is entirely documentation-based and contains no scripts, binaries, or automated command execution logic.
Audit Metadata