authoring-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied HTML data to automatically generate TypeScript pattern files and documentation metadata.
- Ingestion points: Phase 1 identifies HTML templates provided by the user through conversation history or direct pastes as the primary input.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the user-provided HTML from the agent's logic, creating a surface where malicious text in the HTML could influence the generated documentation.
- Capability inventory: The skill has the capability to write new TypeScript files and modify existing ones in the
projects/internals/patterns/src/directory. - Sanitization: Although the skill uses
api_template_validate, this tool focuses on structural HTML validity rather than content sanitization or the detection of embedded instructions. - [DYNAMIC_EXECUTION]: The skill dynamically generates TypeScript code (
.examples.ts) based on user-provided templates and metadata, which is then persisted to the project's source tree. This creates a mechanism where untrusted user content is transformed into renderable code within the application's environment.
Audit Metadata