storytelling-expert
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (drafts, ideas, and data) to generate narrative outputs.
- Ingestion points: User input provided via prompt triggers defined in
SKILL.md. - Boundary markers: Absent; the instructions do not explicitly tell the agent to ignore instructions embedded within the user's draft content.
- Capability inventory: None; the skill only generates text and does not have access to subprocesses, file-writing tools, or network operations.
- Sanitization: Absent; the skill does not perform escaping or validation of the input content.
Audit Metadata