bitbucket-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill points to a remote MCP server at https://rube.app/mcp as the source for the Bitbucket tools. This is a standard configuration for MCP-based skills.\n- [DATA_EXFILTRATION]: The skill is designed to read and manipulate Bitbucket repository data, pull requests, and workspace configurations. This involves processing potentially sensitive code and member information within the agent's context.\n- [COMMAND_EXECUTION]: Provides access to powerful administrative tools like BITBUCKET_DELETE_REPOSITORY and BITBUCKET_CREATE_REPOSITORY. The documentation includes warnings regarding the irreversible nature of deletions.\n- [PROMPT_INJECTION]: The skill features an indirect prompt injection surface due to the ingestion of external data:\n
  • Ingestion points: Reads PR diffs, issue descriptions, and repository listings (SKILL.md).\n
  • Boundary markers: None identified in the provided instructions.\n
  • Capability inventory: Ability to create and delete repositories and modify pull requests (SKILL.md).\n
  • Sanitization: No content sanitization steps are defined for data retrieved from Bitbucket.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:38 AM