app-store-submission-blockers-skill

Warn

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill executes a Python script using a shell heredoc (`python3
  • <<'PY'`) to generate a JWT token for authentication at runtime.
  • [CREDENTIALS_UNSAFE]: The skill instructions involve reading a private key file (.p8) from a path specified by the ASC_KEY_PATH environment variable. While necessary for API access, this involves handling highly sensitive cryptographic material from the local filesystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically the App Store Connect and Google Play APIs, as well as the user's mailbox. This data is then used to diagnose submission blockers, creating a surface where malicious content in those sources could influence agent behavior.
  • Ingestion points: App Store Connect API responses, Google Play track/release state, and the user's mailbox (verdict and issue notices).
  • Boundary markers: None (no explicit delimiters or instructions to ignore embedded content are used during interpolation).
  • Capability inventory: The skill can execute shell commands (curl), run Python scripts, and read files from the local filesystem.
  • Sanitization: No sanitization or validation of the external content is performed before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 2, 2026, 09:42 AM