paper-ds-setup
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality relies on processing external data, which introduces a potential attack surface where malicious instructions could be embedded in design files to influence agent behavior.
- Ingestion points: The skill reads several external sources including
paper-ds.json, token files, component directories, stories, and design system documentation as outlined in SKILL.md (Steps 2 and 3). - Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent to disregard instructions potentially embedded within these ingested data files.
- Capability inventory: The skill possesses capabilities to write versioned project manifests, synchronize design tokens using
paper-ds-tokens, and manipulate canvas artboards viapaper-ds-pagesandpaper-ds-components. - Sanitization: There is no evidence of logic for sanitizing, filtering, or validating the content of external files before the agent acts upon the information.
Audit Metadata