test-runner

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands provided via the 'Commands' input variable. This capability allows for arbitrary code execution within the provided worktree environment.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection. If the 'Commands' input is derived from untrusted sources, such as files in a repository or pull request descriptions, it could be used to execute malicious operations.\n
  • Ingestion points: The 'Commands' and 'WORKTREE' variables defined as inputs in 'SKILL.md'.\n
  • Boundary markers: Absent. There are no delimiters or instructions to ignore embedded malicious content within the provided commands.\n
  • Capability inventory: The skill explicitly instructs the agent to run each command sequentially, enabling full shell access.\n
  • Sanitization: Absent. There is no evidence of command validation, whitelisting, or escaping logic to prevent malicious command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:37 PM
Security Audit — agent-trust-hub — test-runner