slide-deck
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data including source documents, notes, transcripts, and brand guidelines (e.g.,
BRAND.md) to generate slide content. - Ingestion points: External documents and notes provided by the user or found in the working folder (referenced in SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" warnings when processing the source material.
- Capability inventory: The skill has the capability to write a self-contained
.htmlfile to the local filesystem (referenced in SKILL.md under Technical implementation). - Sanitization: There is no mention of sanitizing or escaping the content extracted from source documents before it is interpolated into the generated HTML/JS file.
Audit Metadata