asb-carol-keystones

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill ingests data from STRENGTHS-WEAKNESSES.md and user-pasted text. Boundary markers: The skill uses S-number prefixes but lacks explicit safety delimiters. Capability inventory: The agent is authorized to read and write markdown files in the project directory. Sanitization: The skill does not describe specific sanitization for external content. This surface is assessed as safe as the capabilities are limited to local text file management.
  • [SAFE]: No prompt injection, obfuscation, or safety bypass patterns were detected in the skill logic.
  • [SAFE]: The skill does not perform network operations or access sensitive system paths such as SSH keys, AWS credentials, or environment files.
  • [SAFE]: References to other skills by the same author are used for modular workflow orchestration and do not involve remote code execution or unauthorized dependency installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:32 PM
Security Audit — agent-trust-hub — asb-carol-keystones