handoff

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill demonstrates security best practices by explicitly instructing the agent to redact sensitive information, including API keys, passwords, and personally identifiable information (PII), before saving the handoff document.
  • [COMMAND_EXECUTION]: The instructions require the agent to save the generated document to the operating system's temporary directory. While this is a file system operation outside the immediate workspace, it is a standard method for handling transient data that should not be committed to a repository.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it summarizes untrusted conversation history into a document that will be processed by a subsequent agent.
  • Ingestion points: The skill ingests the entire conversation history and user-provided arguments from SKILL.md.
  • Boundary markers: There are no explicit delimiters instructed for the output document to separate summarized user content from instructions for the next agent.
  • Capability inventory: The skill utilizes file-writing capabilities to the OS temporary directory.
  • Sanitization: The skill contains an explicit instruction to redact sensitive data, which serves as a primary defense against credential exposure during the handoff process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:08 AM
Security Audit — agent-trust-hub — handoff