skills/cedanl/.github/simplify-ceda/Gen Agent Trust Hub

simplify-ceda

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs several shell operations as part of its standard workflow.
  • Uses git diff to identify modified code for review.
  • Uses the claude plugin manager to install its core functionality.
  • Uses air format, uv run ruff format, and uv run ruff check --fix to apply automated code improvements and formatting.
  • [EXTERNAL_DOWNLOADS]: The skill initiates the installation of a plugin requirement from an official source.
  • Fetches the code-simplifier plugin from the claude-plugins-official registry.
  • Provides a reference link to the official claude.com plugin page.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it is designed to read and process untrusted data from source code files.
  • Ingestion points: Reads content from files identified via git diff, including .py, .R, .md, and configuration files as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" headers when passing code content to the sub-agents.
  • Capability inventory: The skill possesses the capability to modify the local filesystem (Phase 3) and execute external formatting tools.
  • Sanitization: The instructions do not specify any validation or sanitization logic for the code being reviewed before it is processed by the agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 07:11 AM