context-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional documentation regarding context engineering best practices and does not contain any executable scripts or malicious commands.
- [SAFE]: Includes explicit security advice for managing project secrets (e.g., '.env' files) and avoiding their inclusion in version control systems.
- [SAFE]: Proactively addresses indirect prompt injection by defining trust levels for loaded context. It instructs the agent to treat data from untrusted sources, such as external documentation or user-submitted content, as non-authoritative data rather than directives to follow.
- [SAFE]: Mentions well-known and standard Model Context Protocol (MCP) integrations such as GitHub, PostgreSQL, and Filesystem for legitimate developer workflows while providing guidelines for safe usage.
Audit Metadata