running-work-transitions
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are purely process-oriented and do not attempt to bypass safety guidelines or override agent behavior.
- [EXTERNAL_DOWNLOADS]: The skill references the official Bitwarden Confluence wiki for the 'Work Transition Playbook'. These references target a well-known service (Atlassian) and the vendor's own domain, which is expected for this type of organizational tool.
- [COMMAND_EXECUTION]: While the skill frontmatter lists Atlassian MCP tools, these are used for structured data retrieval (Jira issues and Confluence pages) rather than arbitrary shell execution or system modification.
- [DATA_EXFILTRATION]: There are no patterns indicating the exfiltration of sensitive information. Data access is scoped to Atlassian resources through authenticated plugins.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources like Jira comments and Confluence pages. While this constitutes a theoretical surface for indirect injection, the skill does not possess exploitable capabilities (like code execution or network sends to third parties) that would make such an attack viable in this context.
Audit Metadata