handoff
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation history and user-provided arguments to generate a handoff document that instructs a subsequent agent on which skills to invoke and what to focus on.
- Ingestion points: The skill reads the entire current conversation history and optional user-supplied arguments described in
SKILL.md. - Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from adopting malicious instructions that may be embedded within the conversation it is summarizing.
- Capability inventory: The skill uses file-writing capabilities to save the generated document to the operating system's temporary directory.
- Sanitization: While the skill explicitly requires the redaction of sensitive data (API keys, passwords, PII), it does not provide mechanisms to sanitize or escape instructions found in the source text that could lead to indirect prompt injection in the next session.
Audit Metadata