ai-pdf-builder
Warn
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the user or agent to execute commands with administrative privileges using 'sudo'. Specifically, it requires 'sudo tlmgr install' to manage LaTeX packages and 'sudo apt-get install' on Linux systems to install the full TeX Live distribution.
- [REMOTE_CODE_EXECUTION]: Core functionality relies on 'npx ai-pdf-builder', which downloads and executes code from the NPM registry at runtime. This execution of unverified remote packages presents a security risk if the package were compromised or substituted.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of large external software suites including Pandoc and BasicTeX/TeX Live. It also triggers additional downloads via the TeX Live Manager (tlmgr) to fetch fonts and formatting libraries from remote TeX repositories.
- [PROMPT_INJECTION]: The skill processes untrusted user-supplied markdown files and text prompts through features like 'enhance' and 'summarize'.
- Ingestion points: Markdown files (e.g., './content.md', './draft.md') and natural language prompts.
- Boundary markers: None identified; content is passed directly to the generator or AI enhancement commands.
- Capability inventory: Subprocess execution (npx, pandoc, latex) and file system writes.
- Sanitization: The skill claims 'Automatic cleanup of AI-generated content', but does not specify sanitization or escaping mechanisms for the input data before it is processed by the AI components.
Audit Metadata