workflow-integration-test
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates as a high-level orchestrator that processes external data from user prompts, workflow registries, and project documentation while possessing capabilities to execute commands and spawn sub-agents.
- Ingestion points: User-provided prompts, the workflow registry (
.claude/workflows.json), project specifications, and test source code. - Boundary markers: Workflows are managed through the
$start-workflowprotocol and a structured task tracking system to separate execution phases. - Capability inventory: Spawns sub-agents (
spawn_agent), executes shell commands via referenced skills (e.g.,$integration-test), and modifies project files. - Sanitization: No explicit sanitization or escaping mechanisms for the ingested data are documented within the skill files.
- [COMMAND_EXECUTION]: The skill directs the agent to run a local Node.js script (
.claude/scripts/lib/workflow-skill-contract.cjs) to regenerate internal contract blocks within the documentation. - [EXTERNAL_DOWNLOADS]: The skill references a 'Python readiness' policy intended to repair or provision missing Python runtimes on Windows, macOS, and Linux to ensure the environment is capable of running integration tests.
Audit Metadata