tour-guide
Warn
Audited by Snyk on Apr 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's Platform Support section (references/platform-support.md) explicitly instructs the agent to "Read [URL]" pointing to a public raw GitHub URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/service-worker/tour-guide/SKILL.md), which means the agent would fetch and ingest open, third‑party content that could contain untrusted instructions affecting behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The Platform Support section explicitly instructs systems to "Read [URL] and install as skill", pointing to https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/service-worker/tour-guide/SKILL.md, which would be fetched and injected into system prompts/configuration (i.e., remote content directly controlling agent prompts), so this is a runtime external dependency that controls the agent.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata