handoff-create
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a user-supplied argument ($ARGUMENTS[0]) to determine the file path for saving the handoff document. If the agent does not sanitize this input, it could potentially be used for path traversal or overwriting files outside of the intended directory.
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates information from the current conversation history, including discoveries and code snippets, to create a persistent document.
- Ingestion points: Current conversation session data (history).
- Boundary markers: The skill lacks explicit boundary markers or instructions to treat session data as untrusted when generating the document.
- Capability inventory: The skill has file-write capabilities (saving to the local filesystem).
- Sanitization: No sanitization or filtering is applied to the content extracted from the session before being written to the handoff file.
Audit Metadata