paper-write
Warn
Audited by Snyk on Nov 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow consumes an optional
-- style-ref <source>argument pointing to arbitrary URLs or local files, but this is an opt-in search/fetch mechanism where the agent actively retrieves specific external material.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill executes
curlto fetch bibliography data from external repositories (dblp.organddoi.org) at runtime, which are common/reputable unofficial operational dependencies.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata