presentation-creation
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and examples are strictly focused on presentation design, narrative structure, and output formatting. No malicious code, network exfiltration, or unauthorized file access was detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (outlines and documents) to generate presentation outputs, which is a potential surface for indirect prompt injection. 1. Ingestion points: The skill accepts 'Source material' such as outlines or document paths as input for presentation generation. 2. Boundary markers: The provided prompt template lacks clear delimiters (e.g., XML tags or block markers) to isolate untrusted user data from the system's instructions. 3. Capability inventory: The skill is capable of generating structured markup (HTML/reveal.js) and code (python-pptx scripts). 4. Sanitization: There are no explicit instructions for the agent to sanitize the input data or to disregard instructions embedded within the source materials.
Audit Metadata