The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill documents a workflow using eval to execute commands extracted from the JSON output of the asc tool via the affordances field. While eval can be risky if data is untrusted, in this context it is used as a mechanism for automating follow-up actions provided by the primary tool itself.
[INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection as it ingests untrusted text data (contact names, email, phone, demo credentials, and review notes) which is then passed to the asc CLI tool.
Ingestion points: Data is ingested via the --contact-first-name, --contact-last-name, --contact-phone, --contact-email, --demo-account-name, --demo-account-password, and --notes flags in the update command within SKILL.md.
Boundary markers: The skill does not employ specific delimiters or instructions to ignore embedded commands within the user-provided text fields.
Capability inventory: The skill uses the asc CLI to interact with App Store Connect services, including getting and updating review details and submitting versions.
Sanitization: There is no evidence of sanitization or validation logic for the input strings provided to the CLI flags.

asc-review-detail