Skills
skills/bigdra50/dotfiles/claude-review/Gen Agent Trust Hub

claude-review

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection due to its processing of untrusted external source code. \n
  • Ingestion points: The skill utilizes the Read, Glob, and Grep tools to ingest content from the code repository. \n
  • Boundary markers: Review prompts for the subagents do not implement isolation delimiters or instructions to ignore instructions embedded within the analyzed data. \n
  • Capability inventory: The skill uses the Task tool to spawn subagents capable of interpreting and reasoning over the provided code content. \n
  • Sanitization: No validation, escaping, or filtering is applied to the source code before it is passed to the AI subagents for review.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:40 PM