user-research-synthesis
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data including interview notes, survey results, and support tickets, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Raw research data provided by the user via the command arguments as described in the framework steps and
argument-hintinSKILL.md. - Boundary markers: The skill instructions do not define delimiters (like XML tags or triple quotes) or provide guidance to the agent to ignore instructions embedded within the provided research data.
- Capability inventory: The skill contains no dangerous capabilities; it lacks file system access, network operations, or shell command execution.
- Sanitization: There are no instructions to sanitize, escape, or validate the content of the ingested research data before processing.
Audit Metadata