newsletter-voice
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-pasted newsletter samples to generate writing instructions in
newsletter-voice.md. - Ingestion points: Newsletter samples provided by the user in Step 1 via chat.
- Boundary markers: Absent. The instructions do not specify using delimiters or 'ignore embedded instructions' prompts when the agent reads the samples.
- Capability inventory: File-write access (
newsletter-voice.md) in the project root. - Sanitization: Absent. The skill extracts patterns directly from the samples without filtering for potentially malicious instructions embedded in the text.
Audit Metadata