webex-voice-interface
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using environment variables (
$MCP_CALLand$TTS_MCP_SCRIPT) to process text-to-speech requests. The usage pattern involves interpolating text into a JSON string inside a shell command, which may be susceptible to command injection if input contains shell-sensitive characters like single quotes.\n- [PROMPT_INJECTION]: The skill ingests untrusted user data in the form of transcribed voice messages and uses it to drive actions across sensitive network automation and management tools.\n - Ingestion points: Voice clip transcripts received via WebEx (SKILL.md).\n
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands within the transcripts.\n
- Capability inventory: The skill has access to pyATS, NetBox, ServiceNow, and various MCP servers (SKILL.md).\n
- Sanitization: Absent; there is no mention of filtering or escaping the transcribed text before it is processed by the agent or the TTS script.\n- [EXTERNAL_DOWNLOADS]: The skill communicates with the WebEx Messages API (
webexapis.com) to upload generated audio files and send text responses. This interaction targets a well-known service required for the skill's primary purpose.
Audit Metadata