github-workflow-automation
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires and executes several external Node.js packages at runtime, specifically
claude-flow@alphaandruv-swarm, which are fetched from the public npm registry vianpxcommands. - [REMOTE_CODE_EXECUTION]: The provided workflow templates include the use of external GitHub Actions such as
ruvnet/swarm-action@v1. This allows for the execution of remote code within the CI/CD environment from a repository that is not included in the verified trusted vendors list. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests untrusted data from the local codebase (
--analyze-codebase), pull request details (gh pr view), and issue tracker content. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate embedded instructions within the ingested data.
- Capability inventory: The skill has the capability to create GitHub issues, pull requests, and comments, as well as execute shell commands and generate new workflow files.
- Sanitization: The skill lacks evidence of sanitization, validation, or escaping of the external data before it is processed by the AI agents or interpolated into command arguments.
Audit Metadata