context-manager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to override agent behavior, bypass safety filters, or extract system prompts were detected.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (e.g., SSH keys, AWS configs), or network exfiltration commands (e.g., curl, wget) are present.
- [Remote Code Execution] (SAFE): The file contains no scripts or commands that download or execute external code.
- [Obfuscation] (SAFE): No hidden characters, Base64 encoding, or homoglyph-based evasion techniques were found.
- [Indirect Prompt Injection] (SAFE): The skill describes a role for building RAG systems that ingest external data, which is a common surface for indirect injection. However, the skill itself provides no implementation code or vulnerable interpolation logic, and it explicitly mentions 'validation and consistency checking' as a trait.
Audit Metadata