screenshot-optimization
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats were detected in this skill. It consists of markdown-based instructions and frameworks for app store marketing.
- [INDIRECT_PROMPT_INJECTION]: The skill attempts to read context from a local file named 'app-marketing-context.md'. While this is an ingestion point for untrusted data, the skill lacks any capabilities to execute commands, write files, or perform network operations, rendering the risk negligible.
- Ingestion points: Reads 'app-marketing-context.md' for positioning and audience context.
- Boundary markers: None explicitly defined in the prompt interpolation.
- Capability inventory: None. The skill only generates text-based advice and plans.
- Sanitization: Not applicable as no high-risk tools are used.
Audit Metadata