asc-aso-audit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various asc CLI commands to fetch app tags, generate search plans, and synchronize keywords. These operations are required for the skill's primary function of interacting with App Store Connect.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and tokenizes user-controlled App Store metadata (description, subtitle, keywords) from local JSON files. This creates a surface for indirect prompt injection where malicious instructions embedded in the metadata could potentially influence the agent's audit results or tool usage.
- Ingestion points: JSON metadata files at metadata/app-info/{locale}.json and metadata/version/{version}/{locale}.json.
- Boundary markers: No specific delimiters are defined in the instructions to help the agent distinguish between data and instructions.
- Capability inventory: The agent can execute shell commands via the asc CLI and access specialized keyword tools via the Astro MCP.
- Sanitization: The instructions do not specify any validation or sanitization steps for the metadata content before processing.
Audit Metadata