asc-crash-triage
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the App Store Connect CLI (
asc). It instructs the agent to execute shell commands to fetch crash logs, beta feedback, and performance diagnostics. While these are legitimate developer tools, the skill requires the ability to execute these external binaries. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from TestFlight crash reports and beta feedback, which could be controlled by external users or attackers.
- Ingestion points: The
asc testflight crashes listandasc testflight feedback listcommands mentioned inSKILL.mdfetch content from external sources. - Boundary markers: There are no explicit instructions for the agent to treat the fetched data as untrusted or to use delimiters to separate instructions from data.
- Capability inventory: The skill utilizes the
ascCLI for data retrieval and includes a file-writing operation viaasc performance download --output ./metrics.json. - Sanitization: No sanitization, escaping, or validation steps are defined for the data retrieved from App Store Connect before it is processed by the agent.
Audit Metadata