navigating-the-initiative-funnel

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill utilizes a suite of Bitwarden-specific Atlassian tools to access internal company data, including Jira issues, issue comments, and Confluence pages. This behavior is expected as the skill's purpose is to guide users through internal software initiatives. The access is limited to the search and retrieval tools specified in the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it is designed to ingest and process data from external sources such as Jira and Confluence that could potentially be edited by unauthorized or malicious actors.
  • Ingestion points: The skill retrieves content through tools like mcp__plugin_bitwarden-atlassian-tools_bitwarden-atlassian__get_issue and mcp__plugin_bitwarden-atlassian-tools_bitwarden-atlassian__get_confluence_page (SKILL.md).
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when handling fetched Atlassian content.
  • Capability inventory: The skill's capabilities are focused on data retrieval and analysis, with the ability to chain into other internal skills using the Skill tool.
  • Sanitization: There is no evidence of filtering or sanitization of the content fetched from Atlassian tools before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:06 PM
Security Audit — agent-trust-hub — navigating-the-initiative-funnel