storytelling-framework
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather context from external files such as
icp-persona,product-positioning, andproduct-messagingto populate the narrative engine. - Ingestion points: Data enters the agent context from user-provided positioning, messaging, and ICP/persona documentation.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for content read from external files.
- Capability inventory: The skill is designed for text and narrative generation; it does not explicitly request or utilize subprocess, network, or file-system write capabilities.
- Sanitization: No sanitization, validation, or filtering mechanisms are described for handling potentially untrusted data from the external input files.
Audit Metadata