shipwright-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
product-agentpackage from the Python Package Index (PyPI) viapip install product-agentto provide its core functionality. - [COMMAND_EXECUTION]: The skill executes the
product-agentCLI and utilizesBashcapabilities (limited topip,npm,npx, andgit) to automate the project scaffolding, dependency management, and testing phases. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary user-provided application descriptions which drive a high-capability autonomous build engine.
- Ingestion points: User-provided plain-English descriptions are collected as the primary input for the build pipeline in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious instructions embedded within the user's application description.
- Capability inventory: The skill has access to
Write,Edit, andBashtools, allowing it to modify files and execute build scripts, which could be abused if the agent follows instructions hidden in the input data. - Sanitization: The instructions do not define any validation, filtering, or sanitization steps for the user-provided text before it is passed to the execution phases.
Audit Metadata