reduce-ai-detection
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, analyze, and transform user-provided text and reference articles, which constitutes a vulnerability surface where malicious instructions embedded in input data could potentially override intended agent behavior.
- Ingestion points: As outlined in the
SKILL.mdworkflow, the agent is expected to receive and process original text segments ("原文") and external reference materials ("参考文章") provided by the user. - Capability inventory: The skill is limited to text generation and reasoning; the configuration does not request access to network tools, file system writes, or subprocess execution.
- Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or unique string markers) or explicit "ignore embedded instructions" commands to separate the user's data from the agent's primary instructions.
- Sanitization: There are no defined mechanisms for validating, filtering, or escaping content within the user-supplied text before it is processed by the agent.
Audit Metadata