paperclip
Warn
Audited by Snyk on Sep 3, 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 required workflow uses the Paperclip CLI to search, read, and process biomedical papers, clinical trials, and regulatory documents from external corpuses (PMC, arXiv, bioRxiv, medRxiv, FDA, clinical trials), which contain outsider-authored free text ingested at runtime.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill includes an installation command that executes a remote bash script from https://paperclip.gxl.ai/install.sh at runtime during setup.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata