skills/openai/plugins/test-triage/Gen Agent Trust Hub

test-triage

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes standard macOS build tools (xcodebuild and swift test) to run test suites. This involves executing shell commands to interact with the local development environment.
  • Indirect Prompt Injection: The skill analyzes external data including test assertions, crash reports, and logs to categorize failures. This creates a potential surface for indirect prompt injection, as malicious instructions could be embedded in test outputs.
  • Ingestion points: Test failure messages, assertion strings, and console logs generated during test execution as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested test data.
  • Capability inventory: The agent has the capability to execute shell commands (xcodebuild, swift test) to interact with the project filesystem.
  • Sanitization: No explicit sanitization or filtering of test output is specified before the data is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:16 PM
Security Audit — agent-trust-hub — test-triage