skills/betterapps-hq/playbook/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes current conversation history to generate a handoff document for consumption by a future agent. This creates a potential surface where malicious instructions within the conversation could be passed to a subsequent session.
  • Ingestion points: The agent's conversation history is used as the input source for the summary.
  • Boundary markers: The instructions do not specify the use of delimiters or safety warnings in the output document to prevent instructions from being interpreted as commands by the next agent.
  • Capability inventory: The skill involves writing a file to the local filesystem (OS temporary directory).
  • Sanitization: The instructions explicitly mandate the redaction of sensitive data, including API keys, passwords, and personally identifiable information (PII) before the document is saved.
  • [COMMAND_EXECUTION]: The skill requires the agent to identify the user's OS-specific temporary directory ($TMPDIR, /tmp, or %TEMP%) to save the resulting document.
  • [SAFE]: The primary functionality is conversation management and summarization, which is consistent with the skill's stated purpose. The use of the temporary directory for ephemeral handoff documents is a standard practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 10:28 AM