detect-prop-drilling

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted React component files which could contain hidden instructions or malicious comments designed to influence the AI agent's behavior or output analysis. * Ingestion points: React component files processed by the agent. * Boundary markers: Absent; no specific delimiters or instructions to ignore embedded content are provided. * Capability inventory: Executes static analysis and generates architectural refactoring advice. * Sanitization: Absent; no validation or cleaning of the source code is mentioned before analysis.
  • [COMMAND_EXECUTION]: The instructions require the agent to run react-docgen or react-docgen-typescript on the local filesystem. Executing tools on external code content is a necessary part of the skill's utility but represents a standard command execution surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:37 PM
Security Audit — agent-trust-hub — detect-prop-drilling