bitbucket
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for retrieving and processing external data from Bitbucket, which introduces a surface for indirect prompt injection attacks.
- Ingestion points: SKILL.md provides commands to fetch pull request data via the Bitbucket REST API v2 (
/pullrequests). - Boundary markers: The provided templates do not include specific delimiters or instructions to the agent to ignore instructions that might be embedded within pull request titles or descriptions.
- Capability inventory: The documented workflows grant the agent capabilities to execute build commands (
npm ci), manage containers (docker build/push), and run deployment scripts (deploy-prod.sh). - Sanitization: The instructions do not demonstrate sanitization or validation of the data retrieved from the Bitbucket API before further processing.
- [EXTERNAL_DOWNLOADS]: The skill references configuration and images from well-known and trusted technology services.
- Evidence: The pipelines use official Docker images (
node:20,node:22-alpine) and interact with the official Bitbucket API endpoint (api.bitbucket.org).
Audit Metadata