asc-crash-triage
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill core functionality relies on executing the
ascCLI tool. It provides a comprehensive set of commands for interacting with App Store Connect data, such as listing apps, fetching crash reports, and downloading performance metrics. This is standard behavior for a triage utility. - [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by design as it is intended to fetch and process untrusted external data.
- Ingestion points: The skill fetches beta feedback and crash reports from App Store Connect via the
asc testflight feedback listandasc testflight crashes listcommands inSKILL.md. - Boundary markers: There are no explicit boundary markers or delimiters defined in the instructions to help the agent distinguish between the fetched data and its own instructions.
- Capability inventory: The agent has the capability to execute shell commands using the
asctool across all tasks defined inSKILL.md. - Sanitization: There is no evidence of sanitization or filtering of the external feedback content before it is presented to the agent for summarization.
Audit Metadata