resolving-mcp-region-configs
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to access and read configuration files in sensitive user directories to identify misconfigured regional endpoints. Affected paths include
~/.claude/,~/.codex/, and~/.gemini/configuration folders. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by taking user input and writing it into configuration files. * Ingestion points: User input for the GCP region string. * Boundary markers: No delimiters or warnings are specified for the injected content. * Capability inventory: File-write access to core agent and plugin configuration files. * Sanitization: No input validation or sanitization process is defined for the user-provided data.
Audit Metadata