brand-voice
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated function of writing style analysis without any detected malicious patterns, unauthorized behaviors, or hidden persistence mechanisms.
- [PROMPT_INJECTION]: The skill ingests untrusted text from external sources such as social media posts and emails to perform linguistic analysis. This constitutes an indirect prompt injection surface; however, the risk is inherent to the primary purpose of style analysis and is managed by instructions to extract specific metadata into a structured schema rather than executing the content. 1. Ingestion points: X posts, articles, essays, emails, and site copy mentioned in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Use of x-api and saving profiles to workspace or memory as described in SKILL.md. 4. Sanitization: Not explicitly implemented in the skill body.
- [COMMAND_EXECUTION]: The skill references the use of the x-api tool for the legitimate purpose of retrieving social media content for analysis. This is a functional requirement and does not represent a security risk.
Audit Metadata