The Agent Skills Directory

[DATA_EXFILTRATION]: The skill manages and accesses sensitive configuration files, specifically ~/.asc/credentials.json and private key files (e.g., ~/.asc/AuthKey_KEYID.p8), which contain App Store Connect API credentials. This behavior is consistent with the skill's primary purpose of authentication management.
[COMMAND_EXECUTION]: The skill relies on executing the asc CLI tool to perform all operations, which is the standard method for this tool's functionality.
[INDIRECT_PROMPT_INJECTION]: The skill interpolates user-supplied data into shell commands for the asc tool, creating an attack surface for indirect prompt injection.
Ingestion points: User-provided inputs for parameters like --key-id, --issuer-id, --name, and --vendor-number in various asc auth commands (SKILL.md).
Boundary markers: None present; the instructions do not include delimiters or warnings to ignore embedded instructions in the inputs.
Capability inventory: The skill has the capability to execute shell commands via the asc CLI tool (SKILL.md).
Sanitization: The skill instructions do not specify any validation or sanitization for the inputs before they are passed to the shell.

asc-auth