customer-whisperer
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted data from external support channels.\n
- Ingestion points: Support tickets are collected from Intercom, Email, Discord, Zendesk, and Help Scout as defined in the 'Analysis Process' and 'Integration Points' sections.\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat input ticket data as untrusted or to ignore any commands found within that data.\n
- Capability inventory: The skill has the capability to generate drafts for FAQs, KB articles, and tutorials, and it includes integration points for publishing to tools like Notion, Confluence, and Linear.\n
- Sanitization: The instructions do not specify any form of sanitization, filtering, or validation for the content pulled from support tickets before it is processed or used in content generation templates.
- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any executable scripts or binary files, which minimizes the risk of direct malicious code execution.
Audit Metadata