kelly-ppt-factory
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data such as slide cards, objectives, and content from external Busabase sources to generate presentations.
- Ingestion points: Data enters the agent's context from multiple Busabase Bases including
projects,decks, andslide-cardsas defined incontent/kelly-ppt-factory-app/app/js/providers/busabase-provider.js. - Boundary markers: The instructions lack specific delimiters or instructions to prevent the agent from following malicious commands embedded within user-supplied slide text or objectives.
- Capability inventory: The skill possesses capabilities for local file system writes (
scripts/generate_pptx.mjs) and network communication via the Busabase SDK. - Sanitization: While basic HTML/XML escaping is present for UI rendering, the skill does not implement comprehensive sanitization or filtering for external content used in prompt interpolation.- [COMMAND_EXECUTION]: The skill documentation and SKILL.md mandate the execution of shell commands and Node.js scripts (
scripts/generate_pptx.mjs,scripts/execute_decisions.mjs) for file generation and workflow management, representing a significant capability surface.
Audit Metadata