The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing the gpd command-line utility. It provides instructions for performing various administrative actions on the Google Play Store, such as gpd publish, gpd monetization, and gpd permissions.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves untrusted data from the Google Play Console. User-submitted reviews fetched via gpd reviews list and crash reports from gpd vitals could contain malicious instructions designed to manipulate the agent's behavior.
Ingestion points: The agent ingests external data through the gpd reviews list and gpd vitals errors reports search commands (defined in SKILL.md).
Boundary markers: The skill does not implement delimiters or safety instructions to prevent the agent from following commands embedded within user reviews or crash logs.
Capability inventory: The agent possesses significant capabilities, including the ability to delete resources (gpd publish edit delete), modify pricing (gpd monetization baseplans migrate-prices), and reply to users (gpd reviews reply).
Sanitization: There are no specified sanitization or filtering processes for the external data before it is processed by the agent.

gpd-cli