write-handoff

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes an explicit instruction to redact secrets, tokens, and personal data, which is a key security safeguard. It also directs all session-specific handoff documents to be written to the system's temporary directory rather than the workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface because it aggregates conversation data into a document intended to serve as a prompt for a future agent. Ingestion points: Processes the current conversation history and user-provided focus arguments. Boundary markers: None explicitly defined for the generated summary. Capability inventory: Performs file-write operations to the OS temporary directory. Sanitization: Instructs the agent to redact secrets and sensitive credentials before writing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 04:13 AM
Security Audit — agent-trust-hub — write-handoff