goal-plan
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the current workspace, code, assets, and infrastructure during the state assessment step, which introduces an indirect prompt injection surface if untrusted files or external code bases are processed.
- Ingestion points: Workspace assets, existing code, and infrastructure configurations are inspected in step 2 ('Assess current state').
- Boundary markers: There are no explicit boundaries or delimiter instructions specified to distinguish between system instructions and analyzed code or asset content.
- Capability inventory: The skill utilizes powerful capabilities including
Bash,Read,Write,Edit, and workflow execution tools (mcp__plugin_ruflo-core_ruflo__workflow_execute). - Sanitization: No sanitization or safety filters are applied to the analyzed asset content before processing.
Audit Metadata