fmc-firewall-ops
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires downloading the CiscoFMC-MCP-server-community from the official CiscoDevNet GitHub repository, which is a trusted and well-known technology provider.
- [CREDENTIALS_UNSAFE]: The configuration instructions specify providing Cisco FMC credentials (FMC_USERNAME and FMC_PASSWORD) via environment variables or plaintext profile files, which poses a risk of credential exposure if the environment is not secured.
- [COMMAND_EXECUTION]: The setup process involves manual execution of shell commands (git, pip, and python) to deploy the external server component required for the skill to function.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by retrieving and displaying firewall rule names and descriptions from the FMC API. Ingestion points: Tool outputs from rule search and inspection tools. Boundary markers: None specified in the documentation. Capability inventory: The skill provides read-only search and query capabilities on the FMC; no rule modification or shell access is present. Sanitization: No specific sanitization or validation of data retrieved from the FMC API is mentioned.
Audit Metadata