aiset-writer
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which introduces a potential vulnerability to indirect prompt injection attacks.\n
- Ingestion points: The skill instructions in
SKILL.mdspecify that users may provide materials in the form of product briefs, news links, PDF files, and voice-to-text transcripts for the AI to process and rewrite.\n - Boundary markers: The skill lacks explicit boundary markers or instructions to the AI to ignore potentially malicious instructions embedded within the user-provided content.\n
- Capability inventory: Based on the provided files, the skill's capabilities are limited to text generation and style transformation. No evidence of file-writing, network communication tools, or code execution capabilities was found.\n
- Sanitization: There are no instructions for sanitizing, validating, or filtering the external content before it is processed by the AI agent.
Audit Metadata