zg-persona-story-collector
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting extensive unstructured user narratives ("Free Dumping" phase) to extract and classify stories. This creates a surface for indirect prompt injection where instructions embedded within a user's story could attempt to influence the agent's classification or summarization logic.
- Ingestion points: Conversational input collected during the interviewing stages described in
SKILL.md. - Boundary markers: The instructions do not define technical delimiters (like XML tags) to separate user content from system instructions, relying instead on conversational flow.
- Capability inventory: The skill is restricted to text processing and generation; it does not request or utilize tools for network access, file system modification, or command execution.
- Sanitization: No automated sanitization or filtering is implemented for ingested text, though the instructions provide a "Quality Check" for the AI to ensure facts are separated from inferences.
Audit Metadata