aimem
Warn
Audited by Snyk on Aug 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill reads prior-agent free text from per-object annotation files on an AIStor Memory FUSE mount (e.g.,
cat .aimem/annot/<object-path>/@all/@<name>), and those annotation contents can be outsider-authored by anyone writing objects in the shared bucket.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata