sensei-align

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of descriptive instructions and configuration metadata. It does not include any executable scripts, binaries, or active commands.
  • [SAFE]: No malicious patterns, such as obfuscation, credential harvesting, or unauthorized network access, were detected. The skill's logic is focused on architectural review and codebase consistency.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by analyzing external code, but it lacks the necessary capabilities to pose a risk.
  • Ingestion points: Processes developer code changes and existing codebase files (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: None (no shell execution, network access, or file-write capabilities are defined or requested).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:29 AM
Security Audit — agent-trust-hub — sensei-align