gsd-profile-user

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present due to the skill's reliance on historical session data for behavioral profiling. * Ingestion points: Processes workspace session logs and interaction history through the profile-user workflow. * Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the analyzed interaction data. * Capability inventory: Utilizes spawn_agent to create sub-agents and performs file-write operations to local artifacts like USER-PROFILE.md and AGENTS.md. * Sanitization: There is no evidence of data sanitization or validation of the session history content before it is processed by the profiler.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:33 AM