asc-subscription-localization

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external tool outputs and using that information to construct and execute follow-up shell commands.
  • Ingestion points: The agent parses JSON and table outputs from several asc ... list commands as described in SKILL.md to resolve IDs and versions.
  • Boundary markers: There are no instructions for using specific delimiters or "ignore" markers when the agent processes these external tool outputs.
  • Capability inventory: The skill performs multiple write operations (asc ... create and asc ... update) across subscription and IAP resources based on the ingested data.
  • Sanitization: The instructions do not specify any validation or sanitization for strings (like names or descriptions) retrieved from the App Store Connect API before they are interpolated into new commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 09:34 PM
Security Audit — agent-trust-hub — asc-subscription-localization