generate-handoff-document
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a legitimate documentation and state preservation workflow. It processes session data through structured subagents and writes results to JSON artifacts and Markdown files as intended.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests conversation history and external tracking files. While it lacks explicit boundary markers to separate data from instructions, the risk is minimal due to the use of rigid output schemas and the absence of high-risk capabilities like network exfiltration or shell execution. * Ingestion points: Conversation history via
CONTEXT_SOURCEand external notes viaTRACKING_FILES. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the subagent instructions. * Capability inventory: The skill is limited to reading project files and writing documentation artifacts. * Sanitization: No input sanitization or validation of the processed text content is defined.
Audit Metadata