The Agent Skills Directory

[SAFE]: The skill serves as a comprehensive educational resource for Atlassian MCP integration patterns and workflow automation.- [SAFE]: Authentication examples in 'references/authentication-patterns.md' correctly utilize placeholders for secrets and explicitly instruct users to adopt secure secrets management services (e.g., AWS Secrets Manager, GCP Secret Manager, or Vault).- [SAFE]: Installation and setup guides for various MCP servers reference reputable official and community-maintained packages with no automated execution of untrusted scripts.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process external content from Jira issues and Confluence pages.
Ingestion points: Untrusted data enters the context through Jira and Confluence search/get tools (e.g., 'jira_get_issue' in 'references/common-workflows.md').
Boundary markers: Implementation examples do not include explicit delimiters to isolate external content.
Capability inventory: The skill facilitates the creation and modification of Jira issues and Confluence pages through various tools.
Sanitization: The main 'SKILL.md' includes mandatory security constraints requiring query validation, input sanitization, and user confirmation for sensitive production operations.

atlassian-mcp