cn-thesis-originality-polish

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted external data from thesis drafts and similarity reports.
  • Ingestion points: The agent is instructed to process user-provided thesis content, match-source excerpts, and AI/AIGC detection reports as detailed in 'static/core/workflow.md'.
  • Boundary markers: The instructions lack specific delimiters or technical boundary markers to separate processed text from agent instructions, which could allow malicious content within a thesis draft to influence the agent's behavior.
  • Capability inventory: The skill's functionality is limited to text generation and logical analysis. No high-risk capabilities such as network operations, file system modification, or subprocess execution are present in the skill files.
  • Sanitization: There are no instructions for sanitizing or escaping the content of the ingested thesis materials before processing.
  • [NO_CODE]: The skill consists entirely of instructional Markdown and configuration YAML files. It does not include or execute any script files (such as .py, .js, or .sh) or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:34 AM
Security Audit — agent-trust-hub — cn-thesis-originality-polish