support-ticket-theme-miner-ecommerce

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions. It does not include any scripts, executable files, or command-line operations that could lead to unauthorized system access or code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as support tickets, chat transcripts, and email samples, creating a potential surface for indirect prompt injection.
  • Ingestion points: Support tickets, chats, email samples, and help center content processed as described in the 'Required input' section of SKILL.md.
  • Boundary markers: Absent. There are no instructions to use specific delimiters or to disregard instructions embedded within the analyzed support content.
  • Capability inventory: None. The skill's instructions are limited to analysis and text generation; it has no capabilities for file system modification, network communication, or subprocess execution.
  • Sanitization: The skill includes explicit guardrails to 'Remove or avoid exposing sensitive customer data' and 'Do not expose personal customer data'.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:24 AM