handoff
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests the current conversation history, which is untrusted data, to generate a summary. This creates an inherent surface for indirect prompt injection if the conversation contains malicious instructions intended to persist in the handoff. * Ingestion points: The 'current conversation' is processed as input. * Boundary markers: Absent; the skill does not define specific delimiters for the conversation content. * Capability inventory: The skill instructs the agent to write files to the OS temporary directory. * Sanitization: Present; the instructions explicitly mandate the redaction of API keys, passwords, and PII.
Audit Metadata