webex-report-delivery
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a formatting guide for delivering reports to WebEx. It defines structured JSON payloads for Adaptive Cards and Markdown templates for various network reporting scenarios (e.g., health checks, security audits).
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process output from other network tools (e.g., pyATS, NetBox). While it ingests external data to create reports, it does not use this data for autonomous execution or decision-making beyond formatting.
- Ingestion points: Data from network audit and health check tools (SKILL.md).
- Boundary markers: Not explicitly defined in templates.
- Capability inventory: WebEx API access (Messages Create/List, Rooms List).
- Sanitization: Not explicitly defined in templates.
- [DATA_EXFILTRATION]: The skill interacts with the WebEx API to post reports. This is the primary stated purpose of the skill. No unauthorized exfiltration of sensitive local files or credentials was observed.
- [COMMAND_EXECUTION]: The skill requires
python3for execution but does not contain or generate arbitrary shell commands. All provided examples are static JSON and Markdown templates.
Audit Metadata