business-document-generator
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions within the skill attempt to bypass safety filters or override the agent's core programming. The content is strictly task-oriented.- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive local files (like SSH keys or AWS credentials) nor does it perform any network requests to transmit data externally.- Obfuscation (SAFE): No encoded strings, zero-width characters, or hidden commands were found; all scripts and documentation are in plain, readable text.- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill relies on standard Python packages from the official PyPI registry (pypdf, reportlab). It does not execute remote code from untrusted URLs.- Indirect Prompt Injection (SAFE): The skill processes user-supplied JSON data to fill templates. While this is an ingestion surface, the data is used for static text rendering within a PDF and is not interpreted as instructions. (1) Ingestion points: scripts/generate_document.py reads JSON data files. (2) Boundary markers: standard JSON parsing. (3) Capability inventory: limited to local file read/write for PDF generation. (4) Sanitization: the PDF rendering process does not execute the input as code or logic.
Audit Metadata