sd2-pe
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues were detected. The skill consists of text-based instructions and does not include any executable scripts or tool requests.
- [NO_CODE]: The skill does not contain any executable scripts, shell commands, or external package dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user-provided text and multimedia metadata. 1. Ingestion points: Processes user text prompts and structured data (JSON) containing asset URLs (Step 2). 2. Boundary markers: No explicit instruction-ignoring delimiters are required for the input data. 3. Capability inventory: The skill has no tools or scripts (0 capabilities). 4. Sanitization: The skill's core purpose is to rewrite input into a restricted engineering format, which inherently sanitizes the structure.
Audit Metadata