fast-ship
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a specific 'Additional Block' format and direct the agent to automatically process project and issue IDs found within these blocks without further user confirmation.
- Ingestion points: Data blocks appended to prompt templates as described in
SKILL.md. - Boundary markers: Content is delimited by specific introductory text and markdown block quotes (
>). - Capability inventory: The
scripts/fast-ship-api.mjsscript enables full REST API interactions including issue creation, modification, and deletion. - Sanitization: The skill requires writing request bodies to JSON files to avoid shell-related injection issues via command-line arguments.
- [EXTERNAL_DOWNLOADS]: The documentation provides a command to install the skill via
npx skills addfrom a GitHub repository (https://github.com/gitbobobo/fast_ship). This repository is owned by the skill author ('gitbobobo') and represents a vendor resource. - [COMMAND_EXECUTION]: The skill suggests a fallback mechanism using
curlwith temporary header files to manage API credentials securely during network operations. - [CREDENTIALS_UNSAFE]: The
scripts/fast-ship-api.mjsscript reads API credentials from~/.config/fast-ship/config.yaml. While this is standard practice for CLI-based API clients, it involves accessing a sensitive configuration file containing an API key.
Audit Metadata