22-personal-brand-context-global

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to gather user input to populate a personal brand context file. Analysis of the instructions and regional templates confirms that no dangerous shell commands, network operations, or obfuscated payloads are present.
  • [PROMPT_INJECTION]: The skill gathers untrusted user input to create a source-of-truth document (.agents/personal-brand-context-global.md) which is consumed by downstream agents. While this creates an indirect prompt injection surface, it is a standard operational requirement for context-gathering skills and no malicious patterns were observed.
  • Ingestion points: User responses to profile and brand questions in SKILL.md (Step 4).
  • Boundary markers: Absent; data is stored in structured markdown sections.
  • Capability inventory: Local file system writes to a hidden directory (.agents/).
  • Sanitization: No explicit sanitization of user strings prior to file writing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 01:42 PM
Security Audit — agent-trust-hub — 22-personal-brand-context-global