claude-automation-recommender
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: Uses shell commands such as
ls,cat, andgrepduring the discovery phase to analyze the codebase. These commands are used to identify the project's language, framework, dependencies, and existing configurations. - [EXTERNAL_DOWNLOADS]: Recommends the addition of external Model Context Protocol (MCP) servers and plugins. These recommendations target established platforms and well-known technology services, including GitHub, AWS, Cloudflare, Supabase, and Sentry.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect injection as it processes untrusted data from the project's environment to generate recommendations.
- Ingestion points: Reads project configuration files (e.g.,
package.json,pyproject.toml) and directory structures usingBashandReadtools inSKILL.mdand referenced templates. - Boundary markers: None identified; the skill assumes the integrity of the files it analyzes.
- Capability inventory: Includes
Read,Glob,Grep, andBashtool access. - Sanitization: No specific sanitization or filtering of file content is performed before analysis.
Audit Metadata