tesla
Fail
Audited by Snyk on Nov 13, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill repeatedly claims complete control of 66 Fleet API commands, but the script implements only about 11 basic commands via the unofficial teslapy library, and the docs do not disclose this gap, which hides a real limitation from the user without any malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required dashboard and location workflows reverse-geocode GPS coordinates via OpenStreetMap Nominatim, a community-edited source the agent fetches without selecting a specific item, so outsider-editable address text reaches the LLM, but an attacker cannot force delivery of a poisoned entry to the user's car location.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The README's quick-start instructs a
git clonethat installs the skill's own code and instructions from an individual-owned GitHub repository, which is an operational inbound dependency from an unofficial but attributable, non-suspicious source, so it is 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