The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines various command-line operations using the gpc tool to interact with monetization APIs. These commands allow listing, creating, and updating in-app products and subscriptions.\n- [PROMPT_INJECTION]: The skill instructions allow the agent to process external data from local files (e.g., product.json, subscription.json) which could serve as a surface for indirect prompt injection.\n
Ingestion points: SKILL.md contains commands like gpc products create --file product.json that read data from the local file system.\n
Boundary markers: No specific delimiters or safety instructions are used to separate the JSON content from the agent's instructions.\n
Capability inventory: The skill possesses the capability to execute shell commands using the gpc utility as seen in SKILL.md.\n
Sanitization: No explicit sanitization or validation of the JSON file contents is performed by the skill before being passed to the CLI tool.

gpc-monetization