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 diffto identify modified code for review. - Uses the
claude pluginmanager to install its core functionality. - Uses
air format,uv run ruff format, anduv run ruff check --fixto apply automated code improvements and formatting. - [EXTERNAL_DOWNLOADS]: The skill initiates the installation of a plugin requirement from an official source.
- Fetches the
code-simplifierplugin from theclaude-plugins-officialregistry. - Provides a reference link to the official
claude.complugin 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 inSKILL.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