sg-mas-trm-expert

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a framework mapping JSON file from a public repository (hackidle.github.io). This file provides the translation between Secure Controls Framework (SCF) IDs and MAS TRM 2021 controls used for compliance assessments.
  • [PROMPT_INJECTION]: The skill is designed to process external organizational data which serves as a potential surface for indirect prompt injection. \n
  • Ingestion points: Technology risk registers, critical system inventories, and board-level risk policies mentioned in SKILL.md. \n
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore instructions embedded in the user-provided risk data. \n
  • Capability inventory: The skill is configured to use Read, Glob, Grep, and Write tools to analyze file systems and generate assessment reports. \n
  • Sanitization: There is no evidence of explicit content sanitization or filtering for the data ingested during the gap assessment process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:26 PM
Security Audit — agent-trust-hub — sg-mas-trm-expert