soia-pkm-library
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 (high risk: 0.85). Required runtime workflow for this skill calls the outsider-authored WeRead
weread-skillsAPI gateway (public network source) and ingests returned JSON fields likemarkText/abstract/content/book metadata into the scripts’ generated Markdown that is then written into the agent’s context/output; this is an indirect prompt-injection path via externally supplied free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata