project-scaffold
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
git init,git add, andgit committo manage the project's version history. These are standard operations for research and development workflows. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided inputs such as project titles, research questions, and target journals to populate metadata files like
project.yamlandREADME.md. This represents a standard input-to-file-write surface common in scaffolding tools. - Ingestion points: User input for project metadata and directory mapping in
SKILL.md(Step 1 and Step 1b). - Boundary markers: None explicitly defined for the interpolation of user strings into YAML/Markdown templates.
- Capability inventory: The skill possesses file system write access for directory and file creation, as well as shell command execution for Git operations.
- Sanitization: No explicit sanitization or escaping logic is described for handling special characters in user-provided metadata strings.
Audit Metadata