orient-status
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md/protocol.yon specify that the skill delegates evidence gathering to a bounded read-only subagent over the provided
scope, which (per the “git tier / plan/doc tier / conversation/folder tier” ladder) can ingest outsider-authored free text from files or conversation turns in that scope (e.g., PLAN/TODO/checklists or recent turns) into the LLM context during the sweep.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata