atlassian
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Atlassian services that could contain hidden instructions targeting the agent.
- Ingestion points: Functions such as
jira_get_issue(retrieving summaries, descriptions, and comments),confluence_get_page(reading page content), andbitbucket_get_file_content(accessing source code) pull data from external, potentially attacker-controlled sources. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing retrieved content.
- Capability inventory: The skill possesses extensive write capabilities across the Atlassian suite, including creating and updating issues, modifying wiki pages, and merging pull requests, which could be abused if an injection is successful.
- Sanitization: The skill does not perform sanitization or filtering on the content retrieved from the APIs before returning it to the agent.
Audit Metadata