fdk
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill employs a bash process substitution pattern to fetch and run a setup script (fdk-kit.sh) from the author's official GitHub repository (github.com/Rheinmir/setup). This mechanism is used to initialize the dev kit sandbox.
- [COMMAND_EXECUTION]: The instructions direct the agent to invoke various local Python and Bash scripts (e.g., ci-local.py, new-skill.py, sync-skill.sh) and use the GitHub CLI (gh) to automate development tasks such as linting, testing, and pull request management.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied descriptions and task specifications to generate HTML-based problem trees and reports. This creates an attack surface where untrusted data is ingested and then rendered.
- Ingestion points: User input describing framework changes or new skills.
- Boundary markers: None explicitly mentioned for the generated HTML output files.
- Capability inventory: Execution of local scripts, file system writes (HTML/JSON), and network operations via standard tools.
- Sanitization: The skill does not describe specific sanitization or escaping of user-provided content before embedding it into the HTML visualization data.
- [EXTERNAL_DOWNLOADS]: Fetches framework components and setup utilities from the author's repository into a project-local directory.
Audit Metadata