run-paid-campaigns-weekly-read
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill performs legitimate data aggregation and performance analysis on marketing metrics.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from marketer exports and the brief's test plan (SKILL.md). While no explicit boundary markers or sanitization logic are defined, a capability inventory shows the skill lacks any high-risk tools (no subprocess calls, file system write operations, or network access), which prevents the ingestion surface from being exploited for malicious purposes.
Audit Metadata