frontend-functionality-docs

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script (scripts/collect-frontend-routes.sh) to automate the discovery of frontend routes. The script relies on the ripgrep (rg) utility to search for file patterns and code strings related to routing configurations.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted source code and documentation to generate functionality summaries.
  • Ingestion points: Reads route entry files (e.g., Next.js pages, Remix routes) and existing documentation files like AGENTS.md found in the repository.
  • Boundary markers: The skill does not implement explicit delimiters or instructions to ignore potential commands embedded within the analyzed source code.
  • Capability inventory: Executes a local shell script for file discovery and has broad read access to project source files to generate documentation.
  • Sanitization: No validation or sanitization of the content from source files is performed before it is presented to the AI for processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:41 PM