mcp-security
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The persona instructions are standard for defining agent behavior and do not include commands to override system instructions or bypass safety filters.
- [DATA_EXFILTRATION] (SAFE): There are no indicators of network activity, credential harvesting, or access to sensitive local file paths.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill contains no executable scripts, shell commands, or external package dependencies.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill utilizes a reference system for its knowledge base. 1. Ingestion points: references/patterns.md, references/sharp_edges.md, references/validations.md. 2. Boundary markers: Absent. 3. Capability inventory: None (the skill defines no tools or commands). 4. Sanitization: Not applicable as no data is being executed or processed for side effects.
Audit Metadata