ask-cli
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
askCLI tool to interact with App Store APIs. It includes commands for retrieving product information, managing subscriptions, and processing transaction refunds. These operations are restricted to the functionality provided by the CLI utility. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external App Store API responses via the
asktool, which could theoretically contain malicious instructions if the source data were compromised. - Ingestion points: Commands such as
ask products list,ask subscriptions get, andask transactions history(SKILL.md) import external data into the agent's context. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the tool's output.
- Capability inventory: The agent can execute CLI commands, including state-changing actions like
ask transactions refund(SKILL.md). - Sanitization: There is no explicit sanitization or validation of the data returned by the CLI tool before it is processed by the agent.
Audit Metadata