The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the asc command-line utility to perform administrative tasks on the App Store, including listing reviews and managing developer responses.
[CREDENTIALS_UNSAFE]: The documentation references and requires access to a sensitive App Store Connect API private key file located at ~/.asc/AuthKey.p8 for authentication.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted customer review text.
Ingestion points: Untrusted data enters the agent context through the asc reviews list and asc reviews get commands in SKILL.md.
Boundary markers: There are no boundary markers or instructions to separate review content from instructions.
Capability inventory: The skill has the capability to execute state-changing commands like asc review-responses create and asc review-responses delete as described in SKILL.md.
Sanitization: The skill does not implement any visible sanitization or validation of the customer-provided text before processing or responding.

asc-customer-reviews