eva-audience-finder
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a clear operational workflow for audience identification and routing. It does not contain any malicious instructions, obfuscation, or unauthorized data access patterns. All file references are to internal paths within the vendor's environment, and there are no network operations or external downloads defined.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text such as topics, hot words, and phenomena as described in SKILL.md. While boundary markers and specific sanitization routines are not explicitly defined in the provided files, the skill lacks capabilities for subprocess execution, file writing, or network operations, effectively mitigating the risk of instructions embedded in external content.
Audit Metadata