user-research-synthesis
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data—including user transcripts, usability test notes, and Slack messages—which may contain malicious instructions designed to influence the synthesis output or agent behavior.
- Ingestion points: Ingests user-uploaded data and reads existing project files from
thoughts/shared/pm/directories. - Boundary markers: The skill does not employ explicit delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested research data.
- Capability inventory: The skill is designed to read and write Markdown files within the
thoughts/shared/pm/workspace. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the ingested content before it is processed and interpolated into reports.
Audit Metadata