persona-roster-expander
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied persona seeds and domain safety rules, creating a potential surface for indirect prompt injection.
- Ingestion points: User-provided inputs including
seed personas,domain, and thesafety rule(SKILL.md). - Boundary markers: The skill does not explicitly define markers to isolate user-provided seed text from the agent's instructions during processing.
- Capability inventory: The skill uses
Writeto createpersonas.json,WebFetch/WebSearchto verify anchors, andAgentto delegate name generation (SKILL.md). - Sanitization: No specific sanitization or escaping logic is described for the user-supplied seed content before it is processed or written to the JSON artifact.
Audit Metadata