advice-standards

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a framework for evaluating external data sources, which creates a theoretical surface for indirect prompt injection attacks.
  • Ingestion points: The skill is intended to be used when analyzing newsletters, blogs, model portfolios, and AI-generated text (as specified in SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific constraints to prevent the agent from executing instructions potentially hidden within the analyzed external content.
  • Capability inventory: The skill is granted access to high-privilege tools: Bash, Read, Write, and Edit.
  • Sanitization: There are no documented procedures for sanitizing or validating the untrusted external content before it is processed by the agent.
  • [NO_CODE]: The skill consists entirely of markdown-based regulatory documentation and compliance logic. No scripts, binaries, or external code dependencies are included in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 01:31 AM