paper-ds-iterate
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data and has the capability to modify the environment, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads user canvas edits, node information, and JSX source code via
get_node_info,get_tree_summary, andget_jsx(SKILL.md, Workflow steps 1 and 2). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate instructions that might be embedded within the read JSX or component data.
- Capability inventory: The skill utilizes tools that can alter the state of the project, including
update_styles,set_text_content,move_nodes, andpaper-ds-land(SKILL.md, Rules and Workflow). - Sanitization: The instructions do not specify any validation, escaping, or filtering of the content retrieved from the canvas before it is used to perform updates.
Audit Metadata