intent-handover-governance
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill does not contain instructions to override agent behavior or bypass safety guidelines. It strictly defines a governance workflow that prioritizes human confirmation.
- [DATA_EXFILTRATION]: No exfiltration patterns or unauthorized network operations were found. The skill explicitly commands the redaction of secrets, API keys, and PII in Rule 8 of
SKILL.md. - [COMMAND_EXECUTION]: The skill utilizes standard version control and repository management tools (
git,gh) to verify the state of the project. These are legitimate tools for its stated purpose of managing development continuity. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from
docs/intent.mdanddocs/handover.md. While processing repository files is an injection surface, the skill includes robust mitigation strategies, such as mandatory consistency checks against the repository's actual state and required human approval for all updates. - [SAFE]: The skill defines a process for documentation and communication between a human and an AI agent, focusing on transparency and verifiable facts.
Audit Metadata