atlassian-readonly-skills

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's Python scripts (e.g., scripts/confluence_pages.py, confluence_comments.py, scripts/bitbucket_files.py, jira_issues.py and others) explicitly call Atlassian APIs to fetch and parse user-generated content from external Atlassian instances (examples in SKILL.md: https://jira.sil.org, https://company.atlassian.net, Bitbucket URLs), and that ingested content is returned and used by the agent as part of its workflow, so untrusted third-party content could indirectly inject instructions.