brand-guidelines

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process user-provided artifacts to apply visual styling, creating a surface where instructions embedded within those artifacts could potentially influence the agent's behavior during the post-processing phase.
  • Ingestion points: The skill accepts "any sort of artifact" as input for brand styling (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the content of the artifact from the agent's instructions (Absent).
  • Capability inventory: The skill utilizes capabilities for document formatting and generation, specifically mentioning technical application via python-pptx (SKILL.md).
  • Sanitization: The instructions do not specify any validation or sanitization routines for the content of the ingested artifacts (Absent).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:03 AM
Security Audit — agent-trust-hub — brand-guidelines