amazon-advertising-strategy
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no code snippets, shell commands, or external dependencies. All logic is contained within the prompt instructions for the AI agent.
- [DATA_EXPOSURE]: While the skill asks users to provide advertising and business performance data, it explicitly states that it has no external API access and does not connect to the internet or any backend services. There is no mechanism within the skill to exfiltrate the data provided by the user.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided data (product details, budget, and performance metrics) to generate advice. While this represents an ingestion surface for untrusted data, the skill lacks any capabilities (such as file writes, network operations, or code execution) that could be exploited via malicious instructions embedded in that data.
- Ingestion points: User messages providing product lines, budgets, and ACoS data (SKILL.md).
- Boundary markers: None present.
- Capability inventory: No subprocess calls, network operations, or file system access identified.
- Sanitization: Not applicable as the skill has no executable capabilities.
Audit Metadata