brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The analysis of the branding guidelines and the Apache license found no malicious patterns, obfuscation, or safety bypasses.
- [NO_CODE]: The skill contains no executable scripts (e.g., .py, .js, .sh); it is purely informational.
- [PROMPT_INJECTION]: The skill defines a process for styling external artifacts, which represents a surface for indirect prompt injection.
- Ingestion points: External artifacts/documents provided by the user for styling (as described in SKILL.md).
- Boundary markers: Absent; the instructions do not define delimiters to separate branding logic from the content of the processed artifacts.
- Capability inventory: Formatting and styling of documents using the well-known python-pptx library.
- Sanitization: Absent; there is no specification for validating or cleaning the content of input artifacts.
- [EXTERNAL_DOWNLOADS]: The documentation mentions dependencies on the python-pptx library and system fonts (Poppins, Lora), but the skill does not perform any automated downloads or installations.
Audit Metadata