brand-voice
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses on natural language processing for brand strategy and does not include any malicious code, obfuscated content, or unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing external data (brand positioning, audience samples, and admired examples). While this represents a potential ingestion surface for indirect prompt injection, the risk is mitigated by the skill's limited capabilities. * Ingestion points: Inputs defined in SKILL.md (e.g., brand positioning, audience needs, external examples). * Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded in the input data. * Capability inventory: The skill is restricted to text analysis and generating a markdown document; it does not possess network access, shell command execution, or high-privilege file system access. * Sanitization: No explicit sanitization or validation of the input content is performed.
Audit Metadata