54-media-plan
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for calculating marketing KPIs and allocating advertising budgets across different platforms (Meta, TikTok, Google). It does not perform any sensitive system operations, network requests, or credential handling.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include reading external context files such as
.agents/product-marketing-context.mdand outputs from other internal skills. - Ingestion points: Reads local context and output files (SKILL.md).
- Boundary markers: None explicitly defined for external content.
- Capability inventory: Limited to generating text-based markdown reports.
- Sanitization: None performed on ingested text.
- Assessment: The risk is minimal as the skill has no dangerous capabilities (no network, no file execution, no shell access) and only generates a planning document.
Audit Metadata