build-guide
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute system commands for tool installation via cargo and for compiling Typst documents into PDFs using the typst-cli.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the typst-cli package from the official crates.io registry if the utility is missing from the environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests various project-specific files that could contain malicious instructions targeting the document generation process.
- Ingestion points: The skill reads project source files including pin_config.h, WIRING.md, README.md, sdkconfig.defaults, justfile, and partitions.csv.
- Boundary markers: No specific delimiters or instructions are used to distinguish untrusted file content from the agent's core instructions.
- Capability inventory: The skill has access to Read, Write, Edit, Grep, Glob, Bash, and Agent tools, which could be leveraged if instructions in ingested files are followed.
- Sanitization: There is no evidence of sanitization or validation performed on the extracted project data before it is interpolated into the Typst template.
Audit Metadata