slide-page-splitter

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate text processing and slide layout planning without any indicators of malicious intent or safety bypass.
  • [EXTERNAL_DOWNLOADS]: The documentation references an installation command npx skills add pointing to the author's official repository (github.com/peter-tu-zynkr/zynkr-skill-builder), which is considered a safe vendor resource.
  • [INDIRECT_PROMPT_INJECTION]: This skill possesses an attack surface for indirect prompt injection as it ingests storyline data from upstream sources. 1. Ingestion points: Data from SLIDE_PACKET ▸ Storyline enters context in SKILL.md (Step 1). 2. Capability inventory: No subprocess calls, network operations, or file-write commands are present in SKILL.md. 3. Sanitization: Step 4 in SKILL.md mandates a human-in-the-loop review to validate output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 07:31 PM
Security Audit — agent-trust-hub — slide-page-splitter