design-and-standards-lead
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external specification files (
specs/PRD.md,specs/ARCHITECTURE.md,specs/DATABASE.md, andspecs/SECURITY.md) to generate new project standards. This represents an indirect prompt injection surface where malicious instructions in the input files could theoretically influence the output specification files. - Ingestion points: The skill reads input from four markdown files in the
specs/directory. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input files.
- Capability inventory: The skill has the capability to write new files to the local file system (
specs/DESIGN_SYSTEM.md,specs/CODE_STYLE.md, andspecs/TESTING.md). - Sanitization: No explicit sanitization or validation is performed on the content of the input documents before they are used to generate the output files. However, this risk is inherent to the skill's primary function of document transformation and is considered a low-severity design trade-off.
Audit Metadata