graalpython-bitbucket-pr

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill reads and processes external data which introduces a risk of indirect prompt injection.
  • Ingestion points: The skill retrieves pull request comments and tasks using gdev-cli bitbucket comment list and gdev-cli bitbucket task list as described in SKILL.md.
  • Boundary markers: There are no instructions providing clear delimiters or guidance to ignore embedded instructions within the fetched Bitbucket data.
  • Capability inventory: The skill can execute shell commands (git push), resolve tasks (gdev-cli bitbucket task resolve), and trigger CI gates (gdev-cli buildbot start-gate).
  • Sanitization: No sanitization or verification logic is present to filter or escape the content of Bitbucket comments before the agent evaluates them.
  • [COMMAND_EXECUTION]: The skill uses several command-line operations to perform its primary functions.
  • It executes git push to upload source branches to the Bitbucket remote.
  • It utilizes gdev-cli, a vendor-specific tool (associated with Oracle/GraalPython), to manage PR creation, comment listing, task resolution, and Buildbot gate monitoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:07 PM
Security Audit — agent-trust-hub — graalpython-bitbucket-pr