test-runner

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill exclusively references standard, well-known testing frameworks and utilities (pytest, jest, cargo, go test, bats). No malicious behavior or suspicious external connections were identified.
  • [COMMAND_EXECUTION]: The skill provides instructions for running local shell commands related to testing, environment inspection (e.g., pip list, npm list), and setup scripts (e.g., ./scripts/setup-test-db.sh). These operations are consistent with the skill's primary purpose of test management.
  • [PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection because it is designed to process untrusted external data:
  • Ingestion points: The agent ingests test output, error logs, and coverage reports as part of its diagnostic workflow (SKILL.md).
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the logs it analyzes.
  • Capability inventory: The skill provides the agent with instructions to execute shell commands for various testing frameworks and local setup scripts.
  • Sanitization: No evidence of data sanitization or filtering was found for the logs processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:17 AM
Security Audit — agent-trust-hub — test-runner