The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (app descriptions, reviews) from the App Store and Google Play. This creates a potential surface for indirect prompt injection where an attacker could theoretically include instructions within an app's store metadata.\n
Ingestion points: App metadata and descriptions are fetched from itunes.apple.com and play.google.com via web_fetch.\n
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potential commands within the fetched content.\n
Capability inventory: The skill utilizes web_search and web_fetch to collect information.\n
Sanitization: There are no explicit sanitization steps for the retrieved text before it is presented to the user or processed by the agent.

appstore-intel