managing-yourself

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from a local context file (.agents/em-context.md) to provide personalized management advice. This ingestion of untrusted local data lacks boundary markers or sanitization, creating a surface for indirect prompt injection. Ingestion points: .agents/em-context.md (SKILL.md). Boundary markers: Absent. Capability inventory: None identified; the skill files only contain instructions for generating conversational responses and do not invoke shell commands or network tools. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 10:46 AM