effect-layers-services
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions to bypass safety filters, override system prompts, or disregard previous instructions were found.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, access to sensitive system files (e.g., ~/.ssh, .env), or unauthorized network requests were detected. The skill operates on local documentation and source files.
- Unverifiable Dependencies & RCE (SAFE): The skill does not attempt to install external packages or execute scripts from remote URLs.
- Indirect Prompt Injection (LOW): The skill encourages the agent to read and search local source code files in
docs/effect-source/. While this creates an ingestion point for potentially untrusted data (if the source files were compromised), it is a standard pattern for technical guidance skills. - Privilege Escalation (SAFE): No use of sudo, administrative commands, or file permission modifications detected.
Audit Metadata