rd-innovator

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data during the scouting and technology assessment phases.
  • Ingestion points: External research, trends, and technology data are processed to generate TECH_RADAR.md and RD_PIPELINE.md entries.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the scouted technology descriptions or research summaries.
  • Capability inventory: The skill primarily performs file writes to the .agile-v/business/ directory to maintain the R&D logs and pipeline.
  • Sanitization: No specific sanitization or validation protocols are defined for handling content from external 'vendor demos', 'conferences', or 'research' sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:07 AM
Security Audit — agent-trust-hub — rd-innovator