workflow
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npx workflowfor various development tasks such as health checks, debugging, and inspecting workflow runs. These commands execute the CLI utility provided by the framework. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by directing the agent to read and process documentation bundled within
node_modules/workflow/docs/and related packages. - Ingestion points: Markdown and MDX files located in
node_modules/workflow/docs/,node_modules/@workflow/ai/docs/,node_modules/@workflow/core/docs/, andnode_modules/@workflow/next/docs/. - Boundary markers: None identified; the agent is instructed to use
grepandglobto retrieve content directly into its context. - Capability inventory: The skill has access to network operations (
fetch), CLI execution (npx workflow), and file system tools (glob,grep). - Sanitization: No sanitization or verification of the documentation content is performed before processing.
Audit Metadata