strix
Warn
Audited by Snyk on Nov 18, 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 CI workflow runs Strix on
pull_requestevents against./, which checks out outsider-submitted PR code (files, comments, README) that the agent then reads, so an outsider can deliver text into the scanned source without the agent selecting a specific item.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill's install path downloads
https://strix.ai/installand executes it withbash, an inbound executable dependency; publisher provenance is plausible (the Strix project's own install channel) but not independently authenticated, since the SHA-256 check is optional and off by default, so under recall-first it is rated medium rather than strong.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata