create-paperclip-bundled-skill
Warn
Audited by Snyk on Nov 11, 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 required Step 0 workflow reads outsider-authored X posts, replies, and keyword search results via the
xcCLI, but the agent first selects a specific post or topic, so exposure is active retrieval rather than a monitored feed.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The build-time GitHub fetch of pinned catalog-ref files (e.g., the mvanhorn/last30days-skill example, whose SKILL.md and scripts become shipped skill material) is an inbound dependency, but the publisher is an individual-owned repository, so it is unofficial; the commit SHA pin is an immutable identifier but does not establish first-party publisher provenance, giving medium.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata