bitbucket-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill facilitates access to sensitive repository data, including source code (via diffs), member lists, and internal issue trackers. This access is restricted to the tools provided by the authenticated Rube MCP environment.
  • [COMMAND_EXECUTION]: Provides functionality for destructive operations such as BITBUCKET_DELETE_REPOSITORY and BITBUCKET_DELETE_ISSUE. The documentation correctly labels these as irreversible and advises the agent to confirm with the user before execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reading pull request diffs, issue contents, and comments. This creates a surface area for indirect prompt injection attacks where an attacker could embed instructions in a PR or issue to manipulate the agent's actions.
  • Ingestion points: BITBUCKET_GET_PULL_REQUEST_DIFF, BITBUCKET_LIST_ISSUES, BITBUCKET_GET_PULL_REQUEST.
  • Boundary markers: Not explicitly defined in the tool instructions.
  • Capability inventory: Includes repository and issue deletion, PR creation, and comment posting.
  • Sanitization: The skill does not specify sanitization routines for processed text before it is re-integrated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — bitbucket-automation