Skills
skills/dishaanand/focusnest/ios-debugger-agent/Gen Agent Trust Hub

ios-debugger-agent

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of untrusted data from the iOS environment.
  • Ingestion points: The agent reads untrusted data from the simulator via mcp__XcodeBuildMCP__start_sim_log_cap (app logs) and mcp__XcodeBuildMCP__describe_ui (UI element labels and identifiers) in SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions to the LLM to ignore instructions embedded within retrieved logs or UI metadata.
  • Capability inventory: The agent has the power to build and execute code using mcp__XcodeBuildMCP__build_run_sim and simulate user interactions via mcp__XcodeBuildMCP__tap and mcp__XcodeBuildMCP__type_text in SKILL.md.
  • Sanitization: The skill does not implement sanitization or validation of external content before processing it in the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:01 AM