handoff

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill aggregates and summarizes the current conversation history, which creates a vector for indirect prompt injection attacks where untrusted user input can influence the next agent's context.\n
  • Ingestion points: The skill summarizes the current conversation history as its primary function (SKILL.md).\n
  • Boundary markers: The skill lacks explicit boundary markers or XML-style delimiters to differentiate summarized content from agent instructions in the final document.\n
  • Capability inventory: The skill is capable of writing files to the operating system's temporary directory (SKILL.md).\n
  • Sanitization: The skill explicitly instructs the agent to redact sensitive information such as API keys and passwords, providing a layer of protection against accidental data exposure (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:39 AM
Security Audit — agent-trust-hub — handoff