The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/detect_gpc.mjs uses execSync to run CLI commands for identifying the GPC installation and configuration state. Evidence includes executions of gpc --version, npx gpc --version, gpc auth status --json, and gpc config get app --json.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files (JSON, CSV) and Base64-encoded payloads, which could contain instructions intended to influence the agent's behavior.\n
Ingestion points: The skill reads from subscription.json, offer.json, product.json, safety.csv, usage-events.json, and Base64-encoded RTDN payloads.\n
Boundary markers: There are no instructions provided to the agent to treat content from these files as untrusted data or to use delimiters to prevent command leakage.\n
Capability inventory: The skill performs administrative actions on the Google Play Console via the gpc CLI, such as creating or deleting subscriptions and products.\n
Sanitization: The instructions do not specify any validation or sanitization routines for the content of the processed files.\n- [EXTERNAL_DOWNLOADS]: The detection script uses npx to check for the GPC CLI, which could lead to the download and execution of the package if it is not already installed.

gpc-monetization