bootstrap-docs
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation templates and configuration files from the author's public GitHub repository (github.com/nesnilnehc/project-documentation-template). This is a standard part of the skill's bootstrapping function.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection (Category 8).
- Ingestion points: Project metadata including project name, description, and technical stack (defined in input_schema and SKILL.md).
- Boundary markers: The skill uses placeholder replacement logic (e.g., [...] placeholders) but lacks explicit security boundaries for untrusted data interpolation.
- Capability inventory: The agent is instructed to write files to the docs/ directory and create a VERSION file on the local filesystem.
- Sanitization: There are no instructions for sanitizing, escaping, or validating the project metadata before it is written into the documentation templates.
Audit Metadata