atomic-note
Warn
Audited by Snyk on Nov 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow pulls external evidence through "appropriate external evidence" and "primary or authoritative external sources" when local material is insufficient, which means the agent actively searches or fetches arbitrary web pages, so outsider-authored text is reachable only after the agent selects it.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill is about authoring Obsidian notes in a vault, which is project-level data rather than system state, but it tells the agent to request unsandboxed CLI execution when a sandbox blocks app attachment, which is a mild bypass of a security mechanism, though it is gated on approval.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata