carousel-writer
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed solely of Markdown documentation and reference materials. It does not include any scripts, binaries, or executable logic.
- [PROMPT_INJECTION]: There is a potential surface for indirect prompt injection because the skill is designed to ingest and repurpose external content, such as blog posts or user-provided narratives.
- Ingestion points: External data is ingested as described in
SKILL.mdfor repurposing into carousel slides. - Boundary markers: The skill does not specify the use of delimiters or structured markers to isolate untrusted input content.
- Capability inventory: The skill can trigger external tools for caption writing, scheduling, and image generation.
- Sanitization: The instructions focus on manual quality checks and brand compliance rather than programmatic sanitization of the input text.
Audit Metadata