frontend-slides
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection attacks where malicious instructions in the input could influence the agent's behavior.
- Ingestion points: The agent ingests user-provided topic briefs, slide outlines, and existing HTML slide files during the 'PPT convert' and 'Enhance existing' workflows defined in SKILL.md.
- Boundary markers: There are no instructions in the skill requiring the use of delimiters or 'ignore' prompts when the agent processes or interpolates these untrusted inputs.
- Capability inventory: The skill allows the agent to generate, modify, and deliver HTML files containing CSS and JavaScript.
- Sanitization: The instructions lack specific requirements for sanitizing, filtering, or escaping the external content before it is included in the final generated presentation.
Audit Metadata