cisco-support-cli

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the cisco-support CLI utility from the NPM registry as a global package during setup.
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands using the cisco-support CLI to retrieve data from Cisco's infrastructure.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through data retrieved from Cisco Support APIs.
  • Ingestion points: Data enters the agent's context through bug descriptions, support case comments, and security advisories fetched via the cisco-support bug, case, and psirt commands.
  • Boundary markers: The skill does not provide instructions to the agent to use delimiters or specific ignore-rules for the content of retrieved API data.
  • Capability inventory: The agent has the capability to execute shell commands via the CLI, which could be targeted by instructions embedded in the API data.
  • Sanitization: No sanitization or structural validation of the API-sourced content is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 05:16 PM