didactic-content-generator
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user input and existing HTML code to generate content, which creates a potential surface for indirect prompt injection. This behavior is inherent to the skill's intended purpose as a content generator. 1. Ingestion points: User-provided topics, target audience descriptions, and HTML source code during the editing process as described in SKILL.md. 2. Boundary markers: No explicit markers or delimiters are defined to isolate user data from agent instructions. 3. Capability inventory: The agent is instructed to read and write the local themes.json file and generate HTML output. 4. Sanitization: The instructions do not specify any sanitization or validation of the input data.
- [EXTERNAL_DOWNLOADS]: The skill references Google Fonts via CSS imports. This is a safe and standard practice for web-based content generation.
Audit Metadata