release-jetbrains
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
gh(GitHub CLI) andgitcommands through Bun's shell API. These tools are used for workflow dispatch, pull request management, repository tagging, and fetching project metadata. While these are high-privilege operations, they are scoped to theKilo-Org/kilocoderepository and are required for the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection.
- Ingestion points: The skill reads external, potentially attacker-controlled data from GitHub PR bodies via
gh pr viewand git commit logs viagit logas described inSKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when providing this external content to the agent for changelog generation.
- Capability inventory: The agent has the capability to commit changes to the repository via the GitHub API (
update-changelog.ts), dispatch GitHub Action workflows (dispatch-prepare.ts), and merge pull requests (watch-publish.ts). - Sanitization: There is no evidence of sanitization or filtering of the ingested PR/commit text before it is processed by the agent.
Audit Metadata