handoff
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
mktemputility to create a temporary file path (mktemp -t handoff-XXXXXX.md). While this is a standard system operation for managing temporary data, it constitutes an instruction for the agent to invoke shell commands. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from the conversation history, user arguments, and external artifacts (PRDs, ADRs, issues) referenced via paths or URLs to create a summary. 1. Ingestion points: User-supplied arguments and external documents referenced via local paths or remote URLs. 2. Boundary markers: Absent; there are no instructions to delimit untrusted content or warn the agent to ignore instructions embedded within the source materials. 3. Capability inventory: The skill has the capability to write to the file system and execute system commands (
mktemp). 4. Sanitization: Absent; the instructions do not require the agent to validate or sanitize the content retrieved from external sources before inclusion in the handoff document.
Audit Metadata