skills/florianbruniaux/claude-code-ultimate-guide/source-command-methodology-advisor/Gen Agent Trust Hub
source-command-methodology-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard discovery commands such as
find,grep,cat, andgit logto gather non-sensitive project metadata like contributor counts and framework hints. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by reading local files into the agent's context. 1. Ingestion points: Reads project configuration files including
package.json,pyproject.toml, andAGENTS.mdin Phase 1. 2. Boundary markers: None identified in the command templates. 3. Capability inventory: Limited to read-only shell commands; no file-write or network-send capabilities are present in the scripts. 4. Sanitization: Content is processed by the model for scoring without pre-filtering. - [EXTERNAL_DOWNLOADS]: The skill references documentation and interactive guides hosted on the author's official domain (
cc.bruniaux.com).
Audit Metadata