writing-ios-unit-tests

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell scripts such as ./scripts/test.sh and ./scripts/check-coverage.sh, as well as system tools like xcodebuild and xcrun simctl. While these are standard for iOS development, they represent a broad command execution surface that depends on the integrity of the project's local environment.\n- [PROMPT_INJECTION]: The skill defines its operational scope using a $ARGUMENTS placeholder which is intended to be filled with user-provided input. This creates an indirect prompt injection surface.\n
  • Ingestion points: The Scope section in SKILL.md directly interpolates user input via the $ARGUMENTS variable.\n
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to treat the user-supplied content as untrusted or separate from the agent's primary instructions.\n
  • Capability inventory: The agent is authorized to execute shell scripts and perform project-wide code analysis based on the defined scope.\n
  • Sanitization: Absent. There is no instruction for the agent to validate, escape, or sanitize the user-provided arguments before they are used to determine the task scope or potentially passed to shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 12:58 AM