open-design-docs
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown data from the user's local file system to generate HTML artifacts. This creates a surface where malicious instructions embedded in a Markdown file could potentially influence the agent's behavior during the conversion process.
- Ingestion points: Markdown documents (.md files) identified via user-provided folders or glob patterns in SKILL.md (Step 1).
- Boundary markers: The instructions do not define explicit boundary markers or directives to ignore embedded instructions within the source files.
- Capability inventory: The skill utilizes specialized platform tools including read_open_design_source, prepare_open_design_brief, register_open_design_artifact, and check_open_design_artifact. It also discovery and listing of local files.
- Sanitization: There is no mention of sanitization, escaping, or validation of the Markdown content before it is read and used to construct the output pages.
Audit Metadata