PDF Generator
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes documentation and code examples that interpolate data directly into HTML/CSS strings before generating PDF documents. This implementation pattern lacks sanitization and creates a surface for indirect prompt injection (HTML injection) if an agent uses these patterns to process untrusted external data.
- Ingestion points: User-controlled data dictionaries in
templates.mdandadvanced.md(e.g.,invoice_data,field_data). - Boundary markers: Absent; templates do not utilize delimiters or warnings to ignore embedded instructions in data.
- Capability inventory: The suggested code includes file-writing capabilities through libraries like
weasyprintandpypdf. - Sanitization: Absent; the reference code uses f-strings for HTML assembly without escaping or validating input content.
- [SAFE]: The skill functions as a reference guide. It contains no executable scripts, makes no network requests, and does not attempt to access sensitive system files or credentials. The skill's behavior is consistent with its stated purpose as a provider of implementation guidance.
Audit Metadata