iridescent-lavender-glass-ppt
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes user-provided content (themes, articles, or data) to generate image prompts.
- Ingestion points: User input is processed in 'Step 1: 提炼内容' and interpolated into the 'Prompt Template'.
- Boundary markers: Absent. The skill does not use delimiters or instructions to ignore embedded commands within user-supplied text.
- Capability inventory: The skill utilizes the
image_gentool to generate visual content based on the constructed prompt. - Sanitization: Absent. There is no evidence of input validation or escaping for the user-provided content before it is included in the final tool call.
- [SAFE]: No instances of unauthorized command execution, persistence mechanisms, or credential harvesting were detected. The skill's operations are confined to local prompt construction and internal tool invocation.
Audit Metadata