persona-builder
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as customer reviews and interview transcripts, to generate personas. This creates a surface for indirect prompt injection if the input data contains malicious instructions.
- Ingestion points: The skill ingests external signals including "customer research, interviews, reviews, or sales notes" (SKILL.md).
- Boundary markers: The workflow lacks explicit delimiters or "ignore embedded instructions" warnings to separate untrusted data from the agent's core instructions.
- Capability inventory: No high-risk capabilities, such as subprocess execution, file-writing tools, or network exfiltration, are present in the skill's instructions.
- Sanitization: No sanitization or validation of input data is specified in the workflow.
Audit Metadata