amz-brand-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (Amazon Brand Analytics reports) provided by the user via copy-paste.
- Ingestion points: The skill triggers when a user pastes or describes Brand Analytics data as described in the frontmatter and the "When to use this" section.
- Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the agent to differentiate between report data and potential malicious instructions embedded in that data.
- Capability inventory: The skill has no active capabilities; it uses zero tools and performs no network or file system operations. Its impact is limited to text generation within the session.
- Sanitization: No sanitization or validation logic is present to filter the user-provided data.
Audit Metadata