brand-voice
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest and analyze external samples (emails, posts, website copy), which represents an attack surface for indirect instructions.
- Ingestion points: SKILL.md specifies gathering samples from social media, newsletters, and DMs.
- Boundary markers: No specific delimiting characters or protective instructions are defined for processing these inputs.
- Capability inventory: The skill interacts with 'x-api' and performs workspace operations.
- Sanitization: There are no explicit sanitization steps for the input samples.
- [PERSISTENCE]: Profiles are stored for session reuse or workspace saving. The instructions include a hard rule against creating repository-tracked files containing personal fingerprints without explicit user consent, mitigating typical exposure risks.
- [DATA_EXFILTRATION]: Uses 'x-api' to pull recent posts for analysis. This interaction is consistent with the skill's purpose and uses standard, non-malicious tool patterns.
Audit Metadata