bitbucket-pr-management
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from Bitbucket, including pull request comments and descriptions, which could potentially contain malicious instructions designed to manipulate the agent.
- Ingestion points: External data enters the agent context via
scripts/bitbucket-cloud-pr.shthrough commands likepr-detailsandread-comments. - Boundary markers: The documentation provides guidance on when to read external content and requires verification before mutations, though it does not define explicit delimiters for isolating this content within the prompt.
- Capability inventory: The agent has the ability to execute the provided local scripts, perform network requests to the Bitbucket API, and modify pull request resources (comments, descriptions, and merge status).
- Sanitization: The
scripts/bitbucket-cloud-api.pyhelper script implements robust security measures, including regex validation for all URL components and a custom handler to prevent HTTP redirects, ensuring the transport layer is secure.
Audit Metadata