discover-journey-map

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and process untrusted external data.
  • Ingestion points: The skill explicitly requests and processes external data including interview transcripts, survey results, customer support tickets, and analytics data as described in the 'Inputs' and 'Core principle' sections of SKILL.md.
  • Boundary markers: The instructions do not specify the use of clear delimiters or guardrail instructions to prevent the agent from following potential commands embedded within the research data.
  • Capability inventory: The skill's capabilities are limited to reading files (Read, Grep) and generating Markdown/Mermaid output. It lacks dangerous capabilities like network access, persistent storage, or arbitrary code execution, which mitigates the risk of successful exploitation.
  • Sanitization: There is no mention of input sanitization or validation for the research data before it is incorporated into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:09 PM
Security Audit — agent-trust-hub — discover-journey-map