The Agent Skills Directory

[DATA_EXFILTRATION]: The skill instructions specify the use of a sensitive local file path ~/.asc/AuthKey.p8 which contains an App Store Connect API private key used for authentication.
[COMMAND_EXECUTION]: The skill facilitates the execution of administrative commands using the asc CLI tool, including destructive actions like removing team members and modifying user roles.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from App Store Connect which then influences high-privilege operations.
Ingestion points: Data is pulled from asc users list and asc user-invitations list as described in SKILL.md.
Boundary markers: The skill lacks explicit markers or safety instructions to separate untrusted data from agent commands, making it possible for malicious content in user profiles to influence agent logic.
Capability inventory: The skill possesses capabilities to remove users and modify roles via asc commands in SKILL.md and references/commands.md.
Sanitization: There is no evidence of sanitization or validation of the content returned by the external CLI tool before it is used in logic-gated shell operations.

asc-users