amicus-coalition
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and legal process documentation. It does not contain any executable scripts, binaries, or configuration files that could pose a technical security risk.
- [NO_CODE]: No Python, Node.js, or shell code is present in the skill. There are no package dependencies or external software requirements identified.
- [PROMPT_INJECTION]: The instructions use standard instructional formatting and do not attempt to override AI safety guidelines, bypass system constraints, or extract internal configuration. The use of markers like '[VERIFY]' serves as a safety check for the user rather than an injection attempt.
- [DATA_EXFILTRATION]: While the workflow involves collecting sensitive legal intake data (e.g., roster names, internal sign-offs, red lines), the skill provides no mechanism (such as curl, wget, or API calls) to transmit this data to any external destination.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or credentials were found. The skill uses placeholders like '[VERIFY FORUM]' for missing configuration data.
Audit Metadata