handoff
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to summarize a conversation. It explicitly mandates the redaction of sensitive information, such as API keys, passwords, and personally identifiable information (PII), which is a security best practice for handoff documents.- [INDIRECT_PROMPT_INJECTION]: As the skill processes conversation history (untrusted data) to create a summary, it is theoretically subject to indirect prompt injection. However, the instructions are constrained to summarization and redaction, and the output is directed to a temporary file, which limits the potential for exploiting capabilities.- [DATA_EXPOSURE]: The skill instructs the agent to save the output to the user's OS temporary directory rather than the current workspace. This is a common practice for transient data and does not represent an exfiltration or exposure risk in this context.
Audit Metadata