icp-persona-builder
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external websites.
- Ingestion points: The skill uses
WebFetchto read company websites andWebSearchto gather reviews, case studies, and social signals. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands when processing fetched web content.
- Capability inventory: The skill instructs the agent to write research findings and generated personas to the local filesystem in the
clients/directory. - Sanitization: No sanitization or filtering of the external text is performed before it is used to influence the agent's output and file-writing actions.
Audit Metadata