connection-review

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-controlled note content through the 'obsidian_get_note' tool and has the ability to modify notes via 'obsidian_replace_in_note', creating a surface for indirect prompt injection.
  • Ingestion points: 'obsidian_get_note' calls in Phase 2 of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading note content.
  • Capability inventory: 'obsidian_replace_in_note' tool used for link write-back in Phase 4.
  • Sanitization: No content validation or sanitization is specified before processing note text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:31 AM
Security Audit — agent-trust-hub — connection-review