research-synthesis
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection during the synthesis phase.
- Ingestion points: The skill reads content from
brief.md,hypotheses/graph.md, and individual hypothesis cards (as specified in Step 4) to populate the final report. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potentially malicious commands embedded within the research data.
- Capability inventory: The skill requires file read and write permissions to aggregate data and generate the implementation plans and reports.
- Sanitization: Content extracted from the research artifacts is directly interpolated into
report.mdand the updatedbrief.mdwithout validation or escaping.
Audit Metadata