slide-outline
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection through its ingestion of user-supplied text.
- Ingestion points: The skill collects user input for context, audience, goals, and slide body text in Phase 1 and Phase 2.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user-provided data.
- Capability inventory: The agent writes to
slide-outline.mdandslide-copy.mdbut does not possess network or shell execution tools. - Sanitization: No validation or escaping is performed on user content before it is stored in the workspace.
- [SAFE]: References to
references/drafting-polishing.mdare local and part of the skill's distributed content.
Audit Metadata