paper-ds-canvas
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from project files, creating a surface for indirect prompt injection where instructions embedded in those files could influence agent behavior.
- Ingestion points: The skill reads
paper-ds.jsonand../paper-ds-manage/references/versioning.mdto determine setup state and theme tokens. - Boundary markers: There are no explicit instructions for the agent to treat the content of these files as untrusted data or to ignore any embedded natural language instructions.
- Capability inventory: The agent can execute a wide range of state-changing operations via the Paper MCP, including
write_html,create_artboard,move_nodes, anddelete_nodes. - Sanitization: The skill lacks validation or sanitization logic for the data retrieved from the JSON or markdown configuration files before using it to drive subsequent actions.
Audit Metadata