distill

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from the active thread and the project codebase, creating a surface for indirect prompt injection. Maliciously crafted content in these sources could attempt to influence the agent's logic during the simplification process.
  • Ingestion points: The skill explicitly instructs the agent to gather context from the "current thread or codebase" (SKILL.md).
  • Boundary markers: The instructions include a requirement to stop and call the AskUserQuestionTool to clarify information if the agent has to infer context or if confidence is low.
  • Capability inventory: The skill empowers the agent to suggest or perform deletions of code, components, and files under the "Code Simplification" section (SKILL.md).
  • Sanitization: No specific methods for sanitizing or delimiting external inputs are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 05:50 AM
Security Audit — agent-trust-hub — distill