security-reviewer
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a template and set of guidelines for manual security audits. It does not contain any executable scripts, binary files, or automated network operations.
- [SAFE]: No hardcoded credentials or sensitive file paths (such as SSH keys or AWS configs) are accessed or requested by the skill instructions.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze external code provided via the
$ARGUMENTSparameter, which presents a surface for indirect prompt injection. - Ingestion points: Local files or directories passed via
$ARGUMENTSinSKILL.md. - Boundary markers: Absent; the skill does not define specific delimiters to wrap untrusted code.
- Capability inventory: The agent is instructed to read and analyze code; no tool usage for file writing, network access, or subprocess execution is requested in the frontmatter or instructions.
- Sanitization: Not present, as the skill is intended to process raw code for vulnerability detection.
Audit Metadata