coordinating-implementation-across-teams

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, user-editable sources such as Jira issues and Confluence pages, which could be used to host malicious instructions.
  • Ingestion points: The skill utilizes several tools in the bitwarden-atlassian-tools plugin to fetch data, including bitwarden-atlassian__get_issue, bitwarden-atlassian__get_issue_comments, and bitwarden-atlassian__get_confluence_page.
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard instructions potentially embedded within the Atlassian content being retrieved.
  • Capability inventory: The allowed-tools listed in the frontmatter are restricted to read-only search and retrieval operations within the Atlassian suite. The skill is not granted capabilities for local file writes, arbitrary network requests, or shell command execution.
  • Sanitization: No explicit sanitization or filtering of the content retrieved from external sources is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:53 PM
Security Audit — agent-trust-hub — coordinating-implementation-across-teams