tenant-tone-profiler
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill makes a runtime POST to the Anthropic API (https://api.anthropic.com/v1/messages) to obtain LLM-generated JSON tone profiles which are parsed and then injected verbatim into downstream system prompts, so external content from that URL directly controls agent instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata