skills/paperclipai/paperclip/pr-gardening/Snyk

pr-gardening

Warn

Audited by Snyk on Jul 29, 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). The skill ingests outsider-authored free text from the Paperclip “extract search” results (including issue title/description/comments/work-products) via GET /api/companies/:companyId/search/extract in Stage A, before any specific PR/work item selection is made.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 29, 2026, 10:59 AM

Issues

1

Security Audit — snyk — pr-gardening