context-engineering
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): The skill is strictly informational, providing strategies for handling large context windows and multi-agent workflows. No executable logic is included.
- EXTERNAL_DOWNLOADS (SAFE): Although the metadata mentions an MCP server (@clawfu/mcp-skills), there are no instructions or scripts provided to install, download, or execute external dependencies.
- PROMPT_INJECTION (SAFE): The content focuses on 'Context Engineering' techniques such as summarization and pruning. It does not contain instructions to bypass safety guardrails or extract system prompts.
- DATA_EXFILTRATION (SAFE): There are no file system access or network communication patterns detected in the markdown text.
Audit Metadata