asc-crash-triage

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external, untrusted data from TestFlight beta feedback and crash reports, creating an attack surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data enters the agent context through the output of commands such as asc testflight feedback list and asc testflight crashes list as specified in SKILL.md.\n
  • Boundary markers: The instructions do not define delimiters or specific system instructions to ignore potential commands embedded within the feedback or crash reasons.\n
  • Capability inventory: The skill utilizes the asc CLI tool to list and view data, and it includes functionality to write files to the local system (e.g., asc performance download ... --output ./metrics.json).\n
  • Sanitization: There are no instructions for the agent to sanitize, validate, or filter the external content before processing and presenting it to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:56 PM
Security Audit — agent-trust-hub — asc-crash-triage