handoff
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command sequence (
f=$(mktemp "${TMPDIR:-/tmp}/handoff-XXXXXX") && mv "$f" "$f.md" && echo "$f.md") to determine a temporary file path for saving the handoff document. While the logic is intended for path generation, it constitutes instructions for arbitrary shell execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user arguments and conversation history to tailor the handoff document, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: User-provided arguments and the current conversation history are used as input for the document content (SKILL.md).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill has the capability to write files to the local file system (specifically the /tmp directory).
- Sanitization: Absent. There is no mention of sanitizing, escaping, or validating the input data before it is summarized and written to the handoff document.
Audit Metadata