storytelling-super-skill
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill logic is focused entirely on text analysis, restructuring, and coaching using safe LLM instructions.
- [EXTERNAL_DOWNLOADS]: The skill's reference documentation includes links to Apple Books, Barnes & Noble, and the World Economic Forum. These are well-known services used for providing grounding context and do not represent a security risk.
- [PROMPT_INJECTION]: The skill is designed to ingest and process user-provided drafts for analysis. This creates a surface for indirect prompt injection (Category 8). 1. Ingestion points: Reading user draft material in SKILL.md. 2. Boundary markers: None defined. 3. Capability inventory: No dangerous capabilities (no file writes, network requests, or shell access). 4. Sanitization: None. This surface is considered safe as the skill has no dangerous tools to exploit.
Audit Metadata