skills/zernie/vigiles/test-harness/Gen Agent Trust Hub

test-harness

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_CONTEXT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and testing project configuration files, which represents an ingestion surface for potentially untrusted data.\n
  • Ingestion points: The agent is instructed to locate and process files such as .claude/settings.json, .claude-plugin/plugin.json, hooks/hooks.json, and SKILL.md.\n
  • Boundary markers: There are no explicit instructions to the model to ignore embedded prompts in the analyzed files during the discovery phase.\n
  • Capability inventory: The skill has access to powerful tools including Bash, Edit, and Write.\n
  • Sanitization: The documentation highlights the use of a sandbox (bubblewrap) and a { trusted: false } flag for testing hooks, providing a layer of protection against malicious scripts.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to install dependencies and run the vigiles test runner as part of its core functionality.\n- [EXTERNAL_DOWNLOADS]: The skill fetches the vigiles package and the claude CLI from the npm registry, and references a GitHub Action from the author. These resources are related to the skill's purpose and originate from the author or well-known services.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill documentation refers to the dynamic context injection syntax (!command) to provide examples of how to test injected context in the Claude Code harness.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 08:59 PM
Security Audit — agent-trust-hub — test-harness