security-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides detailed security specifications for multiple languages (Go, JavaScript, Python) and frameworks (Express, Next.js, React, Vue, Django, FastAPI, Flask). These documents align with industry standards such as OWASP.
- [SAFE]: Explicit safety constraints are included in all reference files, instructing the agent to never commit, log, or request secrets (API keys, passwords, etc.).
- [SAFE]: The skill includes an 'Anti-Patterns' section that explicitly warns the agent against treating external content, logs, or tool responses as trusted instructions, which helps mitigate indirect prompt injection risks.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes project files to generate security reports and apply code fixes.
- Ingestion points: The agent reads codebase files during 'Workflow' and 'Active Audit' modes.
- Boundary markers: The 'Anti-Patterns' section explicitly instructs the agent to not treat external content as trusted instructions.
- Capability inventory: The skill allows the agent to write reports, suggest code fixes, and perform git commits.
- Sanitization: While no automated sanitization is present, the agent is instructed to use a 'Verification Protocol' and human review checkpoints before applying fixes.
Audit Metadata