webinar-content-and-events
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes external, untrusted content like webinar transcripts and presentation slides.
- Ingestion points: Processes webinar transcripts, video files, and presentation slides in Part 2 (Webinar Content Repurposing).
- Boundary markers: None defined to isolate or ignore instructions embedded within the ingested transcripts.
- Capability inventory: The skill specifies writing generated content drafts to the local workspace filesystem under
content/<platform>/drafts/. - Sanitization: No input validation or content filtering mechanisms are specified for the ingested data.
- [EXTERNAL_DOWNLOADS]: The skill references Unsplash for fetching image assets in the slide deck generation schema.
- Evidence: The slide deck JSON structure in Part 1 (Webinar Registration Pages) includes placeholder URLs targeting
https://source.unsplash.com/.
Audit Metadata