Prompt injection instructions
Warn
- Finding
- Prompt-injection style instruction pattern detected.
Claude Code Agent SDK
Security checks across static analysis, malware telemetry, and agentic risk
Overview
No artifact-backed suspicious behavior could be identified, but the workspace files could not be inspected in this run.
This review has low confidence because the workspace inspection commands failed before metadata.json and artifact files could be read. Re-run the scan in an environment where the artifacts are accessible before relying on this result.
Static analysis
Prompt injection instructions
Warn
- Finding
- Prompt-injection style instruction pattern detected.
Prompt injection instructions
Warn
- Finding
- Prompt-injection style instruction pattern detected.
VirusTotal
66/66 vendors flagged this skill as clean.
Risk analysis
No visible risk-analysis findings were reported for this release.