adversarial-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill functions as a template generator that incorporates user-provided task descriptions into an orchestration prompt, creating an inherent surface for indirect prompt injection.\n
- Ingestion points: User input provided through the
[task description]argument inSKILL.md.\n - Boundary markers: The template lacks explicit delimiters or instructions to ignore potential commands embedded within the user-supplied task description.\n
- Capability inventory: The resulting prompt directs the agent to perform file system modifications and execute shell commands including
git,build, andtestas part of its consolidation step.\n - Sanitization: No sanitization or validation of the input is performed before it is interpolated into the workflow template.
Audit Metadata