affiliate-performance-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an 'Interview' workflow to collect user requirements for dashboard definitions. This ingestion of untrusted data lacks explicit boundary markers or sanitization logic. However, the skill is restricted to generating textual specification documents and lacks capabilities such as command execution, file system modification, or network access, which significantly mitigates the potential impact of such an injection.
Audit Metadata