skills/stuartf303/sorcha/yarp/Gen Agent Trust Hub

yarp

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No attempts to override agent behavior or bypass safety filters were detected.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive file paths. All network examples (curl) target localhost for testing.
  • [Obfuscation] (SAFE): No encoded commands, zero-width characters, or homoglyphs were found.
  • [Unverifiable Dependencies & RCE] (SAFE): The skill does not perform external package installations or execute remote scripts.
  • [Indirect Prompt Injection] (SAFE): While the skill interacts with external documentation sources via mcp__context7 tools, there is no evidence of unsafe interpolation or exploitation vectors in the provided templates.
  • [Command Execution] (SAFE): Bash usage is restricted to standard infrastructure management commands (e.g., docker-compose, curl) for local development.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM