workflow-research
Warn
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to execute local JavaScript files using the
noderuntime (e.g.,.claude/scripts/lib/workflow-skill-contract.cjsand.claude/scripts/lib/workflow-manifest.cjs). This allows the execution of arbitrary logic contained within the project's subdirectory. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to research and synthesize information from external web sources, which represents a surface for indirect prompt injection. * Ingestion points: External web content fetched via the
$web-researchchild skill. * Boundary markers: The workflow utilizes a mandatory$knowledge-reviewquality gate to verify artifacts and check for bias, which provides a layer of oversight. * Capability inventory: The skill has permissions to spawn sub-agents, write research artifacts to the local filesystem (tmp/reports/,docs/knowledge/), and execute local scripts via shell commands. * Sanitization: The instructions do not specify programmatic sanitization or escaping of the raw external data before it is processed by the model.
Audit Metadata