mck-ppt-design
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user content to generate presentation slides. This creates an attack surface where instructions embedded in the user's content could potentially influence the agent's actions during the design or generation phases.
- Ingestion points: User-supplied content covering strategy, analysis, and recommendations (SKILL.md).
- Boundary markers: None identified in the framework description to distinguish user data from agent instructions.
- Capability inventory: The skill utilizes Python-pptx to generate and modify .pptx files and includes a cleanup function (SKILL.md).
- Sanitization: No explicit sanitization or filtering of user content is mentioned before it is processed for slide generation.
- [DYNAMIC_EXECUTION]: The skill's workflow involves generating and executing Python code at runtime to create presentation files based on design specifications.
- Evidence: 'Step 4: Python-pptx Generation' in SKILL.md specifies the generation of production-ready files via automated code execution.
Audit Metadata