The Agent Skills Directory

[SAFE]: The skill contains no executable code or scripts. It serves as a structured set of instructions for the agent to act as a marketing expert.
[SAFE]: No network operations, external downloads, or data exfiltration patterns were detected. All recommendations are generated text-based outputs.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from app-marketing-context.md and user-supplied App IDs. However, it lacks any dangerous capabilities (such as subprocess calls, network access, or file-writing tools) that would allow this data to cause harm. The injection surface is limited to influencing the agent's textual marketing advice.
Ingestion points: app-marketing-context.md (read for context), user-provided App ID and target audience.
Boundary markers: Absent.
Capability inventory: No code execution, network, or file-write capabilities detected.
Sanitization: Absent.

screenshot-optimization