crafting-voice-identity
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional tool for brand voice identity crafting. No executable code, network requests, or privilege escalation patterns were identified in the analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data provided by the user to generate brand guidelines.
- Ingestion points: User responses to the discovery questions, including current marketing materials and competitor descriptions (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: None. The skill performs only text generation and does not invoke any system tools or network protocols.
- Sanitization: None detected.
- The risk is minimal as the agent lacks the capabilities to perform actions beyond providing text responses based on the input.
- [NO_CODE]: The skill does not include any scripts, binary executables, or package dependencies, significantly reducing the attack surface.
Audit Metadata