The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including app store descriptions, metadata, and user reviews from Apple App Store and Google Play (Section 3.1, 4, 5, 16.6).
Ingestion points: External metadata fields and user reviews accessed through APIs or local directory structures (fastlane metadata).
Boundary markers: The skill does not define specific delimiters or 'ignore' instructions for the external content it processes.
Capability inventory: The skill utilizes Read, Grep, and Glob tools and interacts with CLI scripts (python, node) to process data.
Sanitization: There is no evidence of sanitization or filtering applied to the untrusted strings before they are processed by the agent.
[COMMAND_EXECUTION]: The skill provides specific CLI commands and script execution patterns to be used by the agent, including pnpm discoverability:audit:aso, python scripts/discoverability-sdk.py, and fastlane operations (Section 9.3, 11).
[EXTERNAL_DOWNLOADS]: The skill references and encourages the installation of external dependencies and tools, such as the aso npm package and various third-party ASO intelligence services (Section 9.2, 16.6.3).
[DYNAMIC_EXECUTION]: The instructions include examples of dynamic code execution via the shell, specifically using node -e to execute inline JavaScript for keyword scoring and analysis (Section 16.6.3).

app-aso