ideal-customer-profile

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external research data, which constitutes a potential injection surface if the data contains malicious instructions.
  • Ingestion points: The skill ingests data via the $ARGUMENTS variable, including survey responses, interview transcripts, and customer feedback (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the ingested research data from the system prompt or to instruct the agent to ignore embedded commands.
  • Capability inventory: The skill is purely informational/instructional and does not list any allowed-tools or script-based capabilities in its definition.
  • Sanitization: The skill does not specify any validation, filtering, or escaping techniques for the external data it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:27 PM
Security Audit — agent-trust-hub — ideal-customer-profile