bitbucket-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires connection to a remote MCP server at
https://rube.app/mcpto fetch tool schemas and execute Bitbucket operations. - [COMMAND_EXECUTION]: The skill exposes high-impact tools such as
BITBUCKET_DELETE_REPOSITORYandBITBUCKET_DELETE_ISSUEwhich perform irreversible actions on the user's Bitbucket workspace. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted data from external repository contributors.
- Ingestion points: Untrusted data enters the agent context via
BITBUCKET_GET_PULL_REQUEST,BITBUCKET_LIST_ISSUES, andBITBUCKET_GET_PULL_REQUEST_DIFF(fetching PR descriptions, issue comments, and code diffs). - Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore embedded instructions in the fetched data.
- Capability inventory: The skill possesses the ability to create, update, and delete repositories, issues, and pull requests.
- Sanitization: There is no mention of sanitization or filtering of external content before it is processed by the agent.
Audit Metadata