handoff

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It processes untrusted conversation history to generate a handoff document that explicitly includes a 'suggested skills' section. This allows instructions from the current chat to influence the behavior of the next agent picking up the task.
  • Ingestion points: Processes the 'current conversation' history (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore embedded instructions in the history.
  • Capability inventory: The skill generates a file saved to the operating system's temporary directory.
  • Sanitization: The skill includes an instruction to redact sensitive information (PII, keys), but lacks sanitization or validation for instructional content found in the chat history.
  • [SAFE]: The skill saves data to the operating system's temporary directory rather than the current workspace. While this involves writing files outside the project context, it is a standard practice for transient session data and is not inherently malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 10:37 AM
Security Audit — agent-trust-hub — handoff