typst-devcontainer-pandoc-setup
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a Docker image from GitHub Container Registry (
ghcr.io/1solomonwakhungu/typst-dev-container/typst). This is a standard operation for configuring development containers and utilizes a well-known container hosting service. - [COMMAND_EXECUTION]: The skill executes shell commands to compile documents and verify tool versions, including
typst,pandoc, andrustc. These commands are standard for the toolset and required for the skill's primary function of document processing and verification. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data to perform document conversion and compilation, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads project-level configuration (
.devcontainer/devcontainer.json) and document files (.typ,.md) from the workspace inSKILL.md. - Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the guidelines for document processing.
- Capability inventory: The skill utilizes shell command execution via the
typst,pandoc, andrustcbinaries as documented inSKILL.md. - Sanitization: No explicit sanitization or validation of the contents of the processed document files is mentioned.
Audit Metadata