moli-webfetch
Fail
Audited by Snyk on Nov 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's install step pipes a remote script from a GitHub release straight into
sh/iexwithout a checksum or signature check, which is sketchy but appears to be the project's own documented installer rather than an attempt to attack the user.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow fetches live web pages at agent-selected or user-supplied URLs (the seed fetch, multi-page research, and crawl link-following), so outsider-authored page text reaches the LLM only after the agent chooses to fetch it, which is the low tier.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs an inbound setup fetch that pipes a
latestinstaller from a GitHub release oflexmount/molidirectly intoshoriex, which is executable code; the org appears to be the project's publisher, but no digest or signature is verified and first-party vendor status is not independently established, so it falls to common/reputable unofficial, medium.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata