presentation-slide-outliner
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for processing untrusted data from user requests regarding presentation outlines. If malicious instructions are embedded in these requests, the agent might inadvertently execute them using its available tools.
- Ingestion points: User requests and visual content descriptions for presentation slide outlines as specified in the SKILL.md file.
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to treat user data as non-executable content.
- Capability inventory: The skill is configured with access to tools including Bash(cmd:*), Write, Edit, Read, and Grep, enabling broad file and system interaction.
- Sanitization: There are no defined sanitization or validation routines to check the content of user-provided outlines before processing.
Audit Metadata