campaign-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from user-provided URLs and creative assets to build Spotify Ads campaign strategies, creating a surface for indirect prompt injection.
- Ingestion points: The skill browses landing page URLs, product pages, and brand briefs to extract brand information, offers, and CTAs (SKILL.md, Workflow Step 1).
- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions found within the processed external content.
- Capability inventory: The skill utilizes an internal API wrapper script (
api-request.sh) to perform GET and POST operations to the Spotify Ads API, including audience and bid estimation endpoints. - Sanitization: The instructions do not specify any sanitization, filtering, or escaping techniques for the content extracted from external URLs before it is used to generate the strategy.
Audit Metadata