pptx-deck-builder
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate instructions for presentation generation using local CLI tools. No evidence of prompt injection, data exfiltration, or malicious code execution was found.
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes user-provided YAML files into slide content. This is a fundamental part of the skill's primary purpose and is implemented with safety-conscious instructions.
- Ingestion points: User-provided YAML files containing slide data (SKILL.md).
- Boundary markers: Absent; however, the instructions emphasize faithful mapping of all fields as an authoritative source.
- Capability inventory: Execution of pptx and excal CLI tools for manifest initialization, layout discovery, diagram rendering, and deck building (SKILL.md, references/pptx-workflow.md).
- Sanitization: Absent; however, the risk is mitigated by explicit instructions to perform faithful conversion without reinterpretation of the content, which prevents the agent from being manipulated by instructions embedded within the data values.
Audit Metadata