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
$ARGUMENTSvariable, 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-toolsor 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