session-handoff-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes internal Python scripts to process session metadata and validate generated prompts. These scripts are executed locally using standard library modules and are strictly scoped to processing transcript and workspace data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources, specifically user-provided session logs and transcripts. It mitigates injection risks by instructing the agent to treat this data as evidence only and not as executable commands. Furthermore, it employs a structured output contract with fact-reliability labels ([verified], [inferred], [unverified]) to prevent the agent from misinterpreting external content.
- [DYNAMIC_EXECUTION]: The skill includes a test suite that dynamically loads other local scripts using Python's
importlib. This execution is confined to the skill's own source files and is used exclusively for functional verification during the development workflow.
Audit Metadata