Skills
Navigate
skills/open-gsd/gsd-core/gsd-profile-user/Gen Agent Trust Hub

gsd-profile-user

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes session history to build a behavioral profile. Instructions or malicious patterns embedded in data processed during those sessions could bias or influence the profiling agent's conclusions.
  • Ingestion points: Session scanning and questionnaire responses (SKILL.md).
  • Boundary markers: The skill mentions a "consent gate," but there are no defined technical delimiters or "ignore" instructions for the session content being analyzed.
  • Capability inventory: The skill uses the Bash, Write, and Agent tools to create or modify local artifacts like USER-PROFILE.md and CLAUDE.md.
  • Sanitization: No explicit sanitization or filtering of the analyzed session data is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 07:49 PM