frontend-stack
Warn
Audited by Snyk on Nov 21, 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 identity and direction workflow has the agent WebFetch and inspect arbitrary competitor and reference websites (chosen by the agent, not forced on it), which is low-risk selected web content rather than a feed outsiders can push into.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The only instructed inbound setup path is the router's
/plugin marketplace add JaimeJunr/claude-code-indie-dev-stackcommand, which installs plugin material from an individual-owned repository, so it is unofficial with no warning signs (medium), while the Remotionnpx skills add remotion-dev/skillspath is first-party and the remaining URLs are static documentation or subjects of research.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's only state-changing operations are suggested agent-integration installs (
npx skills add remotion-dev/skillsand/plugin marketplace add), which pass gate 1, but no irreversible operational loss is established, so gate 2 fails.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata