slide-planner
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions and metadata found no evidence of prompt injection, data exfiltration, or unauthorized command execution. The workflow relies on standard text processing and internal platform tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied material to generate slide outlines and content, which presents a surface for indirect instructions.
- Ingestion points: The skill ingests user-provided material via the initial prompt as defined in the workflow.
- Boundary markers: No specific delimiters or boundary markers are instructed for the user-supplied content.
- Capability inventory: The skill utilizes internal presentation tools to generate .pptx files and speaker notes.
- Sanitization: The skill mitigates risks by requiring an explicit human-in-the-loop confirmation step for the outline before final deck generation, and a final formatting review before delivery.
Audit Metadata