handoff
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
mktempcommand via the shell to create a temporary file path for storing the handoff document. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation history and user-supplied arguments to generate its summary, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads the current conversation history and user-provided arguments as described in the prompt.
- Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the conversation data.
- Capability inventory: The skill allows the agent to execute shell commands (
mktemp), read files (explicitly instructed to read the temporary file), and write files to the system. - Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested conversation content before it is processed.
Audit Metadata