fiber-report

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests data from external ADVA ALM devices to populate an HTML audit report.
  • Ingestion points: Data enters the agent's context through MCP tools alm_list_alarms, alm_get_port, and alm_get_measurement_history which fetch state from physical hardware.
  • Boundary markers: The skill lacks explicit delimiters or "ignore instructions" warnings when interpolating device-provided fields like {PORT_NAME} or {FAILURE_DESCRIPTION} into the final report template.
  • Capability inventory: The skill utilizes file-writing capabilities (alm_download_trace_to_file, generate_alm_diagrams, and manual HTML creation) to store reports locally.
  • Sanitization: There is no evidence of string sanitization or validation for the metadata retrieved from the hardware ports before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:19 PM