handoff
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill summarizes conversation history, creating a surface where malicious instructions embedded in the chat could be processed or propagated to the next agent session.
- Ingestion points: Conversation history context (as processed in SKILL.md).
- Boundary markers: Absent. There are no explicit delimiters instructed to isolate untrusted conversation data from the summarization instructions.
- Capability inventory: The skill performs file-write operations to the OS temporary directory.
- Sanitization: The skill includes a specific directive to redact sensitive data (API keys, passwords, PII), which significantly reduces the risk of accidental data exposure.
Audit Metadata