context-engineering

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions focus on legitimate context engineering tasks such as mode switching (dev, review, research), selective file loading, and token optimization via strategic compaction. No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were detected.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted external data (external research, architecture docs, and code files), this is fundamental to its purpose as a context management tool.
  • Ingestion points: Architecture documentation, active code files, test files, and external research notes specified in SKILL.md.
  • Boundary markers: The instructions do not explicitly define delimiters for untrusted content.
  • Capability inventory: The skill has access to Read, Write, Edit, Bash, Grep, and Glob tools.
  • Sanitization: No specific sanitization or validation logic is defined for processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 06:31 PM