sn-research-synthesis
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's architecture creates a surface for indirect prompt injection by ingesting and processing untrusted data from multiple external sources.\n
- Ingestion points: The skill reads project-specific files including
{report_dir}/request.md,{report_dir}/plan.json, and all markdown files within{report_dir}/sub_reports/.\n - Boundary markers: There are no instructions defining the use of delimiters, XML tags, or triple quotes to isolate the external content from the skill's own instructions.\n
- Capability inventory: The skill utilizes file-system read capabilities for research data and file-write capabilities to generate the
{report_dir}/synthesis.mdoutput.\n - Sanitization: The instructions do not prescribe any validation, escaping, or filtering of the content retrieved from the sub-reports before it is processed by the agent.
Audit Metadata