brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to apply styling guidelines to external artifacts provided as input. This creates a potential surface for indirect prompt injection if the processed content contains hidden instructions.\n
- Ingestion points: External artifacts and text content provided to the agent for styling as described in SKILL.md.\n
- Boundary markers: None identified in the instructions to separate input data from instructions.\n
- Capability inventory: The skill documentation mentions using
python-pptxto manipulate presentation files and apply brand colors and fonts.\n - Sanitization: No specific sanitization, validation, or filtering of input content is mentioned.\n- [NO_CODE]: The skill consists primarily of documentation and style guidelines without accompanying executable script files, reducing the risk of direct malicious code execution.
Audit Metadata