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 process untrusted external data sources such as interview notes, survey responses, and support transcripts.
- Ingestion points: Raw research data is ingested as input for the synthesis process as described in the 'Goal' and 'Steps' sections of SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to treat ingested research data as untrusted, increasing the risk that embedded instructions could influence the agent's behavior.
- Capability inventory: While the skill itself is purely instructional and does not contain code, it does not use the 'allowed-tools' field to restrict the agent's capabilities, potentially allowing access to file system or network tools if provided by the environment.
- Sanitization: The skill includes strong privacy safeguards for PII pseudonymization but does not provide mechanisms to escape or sanitize malicious content within the research data.
Audit Metadata