meta-apply
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime,
/meta-applyreads staged patch files from.aris/meta/pending/(e.g., the.diffandmanifest.jsonl), which are authored by an outsider producer model and then ingested into the fresh codex jury prompt as readable text for the LLM to judge.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata