user-research-synthesizer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to have an agent process and synthesize potentially untrusted external data, such as customer interview transcripts, open-ended survey responses, and feedback tickets. This creates a surface for indirect prompt injection where malicious instructions could be embedded within research data to manipulate the agent's synthesis or recommendations.
- Ingestion points: Raw interview data, survey responses, and support tickets as defined in the "Research Synthesis Methodology" section of SKILL.md.
- Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or to ignore instructions found within the source data.
- Capability inventory: No technical capabilities (such as shell execution or network access) are defined in the skill; it relies on the agent's native text processing.
- Sanitization: Absent; the skill does not suggest any sanitization or validation of the input research data.
- [NO_CODE]: The skill consists entirely of behavioral instructions, templates, and frameworks in Markdown. It does not include any scripts, executables, or definitions for external tool invocation.
Audit Metadata