cf-cli

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the use of the Cloud Foundry CLI to manage cloud applications and infrastructure. Commands include cf login for authentication, cf ssh for accessing application containers, and cf set-env for managing environment configuration.
  • [EXTERNAL_DOWNLOADS]: The instructions include steps to install the Cloud MTA Build Tool (mbt) via npm and the multiapps plugin using the cf install-plugin command. These are well-known tools for the Cloud Foundry and SAP development environments and are retrieved from official repositories.
  • [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it is designed to read and process external data.
  • Ingestion points: The skill consumes data from application logs (cf logs), space events (cf events), and raw Cloud Foundry API responses (cf curl).
  • Boundary markers: No specific delimiters or instructions for isolating untrusted data are provided.
  • Capability inventory: The skill uses the cf CLI which possesses significant capabilities including network access, file system interaction, and resource management.
  • Sanitization: The skill does not define specific sanitization or filtering logic for the data it processes from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:23 PM
Security Audit — agent-trust-hub — cf-cli