output-formatter
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill instructions focus strictly on formatting and do not contain patterns aimed at bypassing AI safety guidelines or overriding system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration commands were detected. The skill has no 'allowed-tools' for network access.
- [Remote Code Execution] (SAFE): No external dependencies, package installations, or remote script downloads are present.
- [Indirect Prompt Injection] (LOW): The skill is a data processor for untrusted agent outputs. 1. Ingestion point: Receives agent outputs in 'SKILL.md'. 2. Boundary markers: Absent. 3. Capability inventory: No tools allowed; no exec/eval capabilities. 4. Sanitization: Absent. Despite being a surface for injection, the lack of capabilities prevents any malicious payload from having a security impact.
- [Dynamic Execution] (SAFE): No runtime code generation or dynamic loading techniques are used.
Audit Metadata