asc-crash-triage

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a guide for using the 'asc' tool to interact with App Store Connect. It does not contain any obfuscated code, hardcoded credentials, or malicious persistence mechanisms. All operations are consistent with the stated purpose of triaging app data.\n- [PROMPT_INJECTION]: The skill instructions involve fetching and summarizing external data such as beta feedback and crash signatures. This introduces a surface for indirect prompt injection where malicious content in the reports could attempt to influence the agent's output. The risk is minimized by the scope of the operations which focus on data retrieval and viewing logs.\n
  • Ingestion points: Data fetched via asc testflight feedback list and asc testflight crashes list as described in SKILL.md.\n
  • Boundary markers: No specific delimiters or 'ignore' instructions are provided for handling the fetched content.\n
  • Capability inventory: Capabilities are limited to asc CLI tool calls for data listing and local file output.\n
  • Sanitization: The instructions do not include steps for sanitizing or escaping the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 02:25 AM