research-synthesizer

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes untrusted content from research-memory/*.md files to generate a strategy brief. This ingestion of external data creates a surface for indirect prompt injection. However, the risk is mitigated as the skill's capabilities are restricted to generating text and writing to specific local files without network or command-line access. 1. Ingestion points: research-memory/ files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File-write access to research-memory/strategy-brief.md and research-log.md. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:00 AM