article-writing
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected in the instructions or metadata. The skill is limited to natural language processing for writing tasks.
- [PROMPT_INJECTION]: The skill defines a process for ingesting external content to capture a writing voice, which is a surface for indirect prompt injection.
- Ingestion points: User-provided articles, newsletters, and social media posts referenced in the 'Voice Capture Workflow' section of SKILL.md.
- Boundary markers: Absent. No delimiters or instructions to ignore embedded commands are specified for the input examples.
- Capability inventory: None. The skill does not request or use any tools, shell access, or network capabilities.
- Sanitization: Absent. No filtering or validation of the provided text examples is performed. The lack of capabilities limits the risk to text output manipulation.
Audit Metadata