handoff
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests conversation history to generate a handoff document for subsequent agents, which creates an attack surface for indirect prompt injection. A malicious instruction in the current conversation could be carried over into the summary and influence the behavior of the next agent.
- Ingestion points: Current conversation history (referenced in
SKILL.md). - Boundary markers: The instructions do not define specific delimiters or boundary markers for the generated content to separate it from the agent's instructions.
- Capability inventory: Writing files to the system's temporary directory (
$TMPDIR,/tmp, or%TEMP%). - Sanitization: The skill provides instructions to redact sensitive information such as API keys and PII, but it does not include measures to sanitize or escape instructions that might be embedded within the conversation text.
Audit Metadata