blog-image
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a prompt-engineering tool that does not invoke external commands, access sensitive system files, or make network requests. All referenced assets are local markdown files within the skill's directory.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests user-supplied content to generate structured prompts. However, the risk is negligible as it lacks executable capabilities.
- Ingestion points: User-provided blog titles and topic descriptions are used in
SKILL.md(Step 1 and Step 3). - Boundary markers: None identified. The user input is interpolated directly into the image prompt template.
- Capability inventory: No capabilities for subprocess calls, file-writing, or network operations were found in any of the skill files.
- Sanitization: There is no evidence of sanitization or filtering of user-supplied text before it is placed into the prompt output.
Audit Metadata