workflow-validate
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes source code in
src/workflows/, which represents a surface for indirect prompt injection where malicious instructions could be embedded in the code files. - Ingestion points: Code files in
src/workflows/and referenced modules. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill body directs the agent to execute local shell commands (
npm run checkandnpm run build). - Sanitization: No input sanitization or validation is specified.
- [COMMAND_EXECUTION]: The skill instructs the agent to run project-specific scripts (
npm run checkandnpm run build), which involves executing commands defined in the project's configuration files.
Audit Metadata