bitbucket-automation
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with untrusted external data, creating a potential surface for indirect prompt injection attacks where malicious instructions hidden in repository content could influence agent behavior.
- Ingestion points: Data is ingested through tools such as
BITBUCKET_GET_PULL_REQUEST,BITBUCKET_LIST_ISSUES, andBITBUCKET_GET_PULL_REQUEST_DIFF, which fetch user-provided text and code changes. - Boundary markers: The instructions lack specific delimiters or guidelines for the agent to distinguish between data content and operational instructions.
- Capability inventory: The skill has access to powerful capabilities including repository deletion (
BITBUCKET_DELETE_REPOSITORY), issue modification (BITBUCKET_UPDATE_ISSUE), and pull request creation, which could be abused if an injection is successful. - Sanitization: There is no mention of sanitization or validation logic for the content retrieved from Bitbucket APIs.
Audit Metadata