workflow-feature
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute a specific local Node.js script (
.claude/scripts/lib/workflow-skill-contract.cjs) with the--writeflag for maintenance purposes. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing data from multiple untrusted or external local sources to drive complex agent behavior.
- Ingestion points: Data is read from several project-level files including
.claude/workflows.json,CLAUDE.md,AGENTS.md, anddocs/project-config.json. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded instructions within these ingested files.
- Capability inventory: The skill has access to shell command execution (
node), the ability to spawn sub-agents (spawn_agent), and the authority to orchestrate a sequence of other automated skills based on ingested data. - Sanitization: The skill lacks explicit sanitization or validation steps for the content ingested from the external configuration files before it is used to influence the workflow logic.
Audit Metadata