engineer-motivation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from local context files that are automatically updated based on conversation history, establishing a surface for persistent indirect prompt injection.
  • Ingestion points: Context is read from .agents/em-context.md and .agents/reports/[name].md.
  • Boundary markers: The instructions do not define delimiters or specific constraints to isolate data retrieved from context files.
  • Capability inventory: The skill has the capability to read from and automatically update (write to) local files to maintain state.
  • Sanitization: No sanitization or validation of the content processed from these files is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 10:46 AM