code-review-assistant
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown content and does not include any executable scripts, binaries, or configuration files.
- [SAFE]: No malicious patterns, obfuscation, or dangerous command execution were detected during the analysis. The instructions promote secure coding practices.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters, override system prompts, or provide jailbreak-style commands.
- [DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or access patterns targeting sensitive local files.
- [REMOTE_CODE_EXECUTION]: The skill does not perform package installations or download/execute external scripts.
- [SAFE]: The skill processes untrusted input (code diffs and file sets), creating an indirect prompt injection surface. However, the skill itself defines no exploitable tools or capabilities.
- Ingestion points: Code diffs or file sets (SKILL.md description)
- Boundary markers: None specified in instructions
- Capability inventory: No subprocess, network, or file-write capabilities are defined
- Sanitization: None described for external input
Audit Metadata