one-pager-builder
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance and templates for creating one-page sales documents. Analysis of the instructions and included artifacts (markdown references, templates, and a Python validation script) found no evidence of prompt injection, data exfiltration, or malicious code execution.
- [COMMAND_EXECUTION]: The skill includes a utility script
scripts/check-output.pywhich is used to validate the presence of required sections in generated deliverables. This script operates locally, does not perform network operations, and relies on standard Python libraries (pathlib,sys) to read and verify local file contents. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external product and company data to generate collateral. 1. Ingestion points: User-provided product descriptions and deliverable files read by
scripts/check-output.py. 2. Boundary markers: No explicit delimiters or warnings for embedded instructions are present in the provided templates. 3. Capability inventory: Local file reading viascripts/check-output.pyand general LLM text generation. 4. Sanitization: No specific sanitization or filtering of external content is implemented. This is documented as a standard operational risk for document-generation skills and does not indicate malicious intent.
Audit Metadata