user-personas
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via external research data. Ingestion points: Analyzes CSV, Excel, and transcript files (SKILL.md). Boundary markers: No explicit delimiters or warnings provided to the agent for processing untrusted content. Capability inventory: Relies on reading and analyzing external data which could contain malicious prompts. Sanitization: No content validation or escaping is specified for the input data.
Audit Metadata