collecting-testflight-feedback

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted feedback text from beta testers on App Store Connect.
  • Ingestion points: Beta feedback text and comments from the TestFlight screenshot feedback page referenced in SKILL.md.
  • Boundary markers: The instructions do not define boundary markers or directives to ignore instructions contained within the ingested feedback text.
  • Capability inventory: The agent has the capability to write to the file system, create directories, and execute shell commands (mkdir, curl).
  • Sanitization: No sanitization or escaping of the feedback text is specified before it is interpolated into the markdown reports.
  • [EXTERNAL_DOWNLOADS]: Fetches image assets from Apple's official TestFlight feedback domain (tf-feedback.itunes.apple.com).
  • [COMMAND_EXECUTION]: Uses shell commands to create the report directory structure (mkdir -p), download screenshots (curl), and retrieve UTC timestamps (date).
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 12:58 AM
Security Audit — agent-trust-hub — collecting-testflight-feedback