The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the external asc CLI tool and a local Node.js script (asc-api.mjs) to execute administrative tasks on App Store Connect.
[DATA_EXFILTRATION]: The skill and its associated scripts access highly sensitive credentials, including Apple API keys, issuer IDs, and .p8 private key files. These are used to authenticate requests to api.appstoreconnect.apple.com. While this involves sensitive data and network operations, it is the primary intended function of the skill and targets an official, well-known service.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted content from external sources that is then processed by the agent.
Ingestion points: The agent reads external data via asc reviews list (user-submitted reviews) and asc metadata (app store descriptions).
Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between its instructions and the data fetched from the App Store.
Capability inventory: The agent has the authority to perform high-impact actions, such as submitting apps for review (asc submit), publishing builds (asc publish), and managing signing certificates or user accounts.
Sanitization: The skill does not mention any mechanisms to sanitize, filter, or validate the content retrieved from App Store Connect before it is processed by the agent.

appstore-connect