brand-identity
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references brand guidelines from trusted organizations including GitHub, IBM, and Wikimedia, as well as reputable design studios like Wolff Olins and Pentagram. These links are provided as research material for the agent to use during identity design tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from reference URLs and existing brand materials. Ingestion points:
references/brand-identity.mdand user-provided inputs. Boundary markers: The skill does not define specific delimiters for external content within the LLM prompt. Capability inventory: The skill is limited to text-based analysis and design documentation; it lacks high-privilege tool access, file system write permissions, or network exfiltration capabilities. Sanitization: No explicit filtering or validation of the retrieved external content is described.
Audit Metadata