real-estate-market

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted codebase files and manifests without boundary markers or sanitization, which creates a surface for indirect prompt injection. Findings: Ingestion points include codebase files; Capability inventory includes filesystem reads and writes to the docs/ directory and telemetry paths; No sanitization or boundary markers are implemented to prevent malicious instructions in the audited code from influencing the agent.
  • [SAFE]: The skill includes a telemetry feature that records execution metadata in the platform's local project directory at ~/.claude/projects/. This operation is confined to the local environment and is used for internal skill improvement.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — real-estate-market