iOS Build Expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill has a vulnerability surface due to ingesting untrusted data from build outputs.\n
  • Ingestion points: Processes output from make sim-build captured in /tmp/build.log.\n
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent when reading log content.\n
  • Capability inventory: The skill allows the use of Bash, Read, Edit, and Grep to act upon findings in the code.\n
  • Sanitization: No sanitization or filtering of the log content is performed before analysis.\n- [COMMAND_EXECUTION] (SAFE): The skill uses standard iOS development tools (make, xcrun, simctl) which are appropriate for the stated purpose of fixing build issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM