tw-research-writing-coach
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and documentation reveals no evidence of malicious intent or security vulnerabilities. The content is consistent with its stated purpose as an academic writing tool.
- [DATA_EXFILTRATION]: The skill does not perform network operations or access sensitive system paths (e.g., credentials, private keys). It strictly operates on user-provided text and local reference documentation.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified third-party packages.
- [PROMPT_INJECTION]: The skill processes user-supplied research paragraphs. While this constitutes an indirect prompt injection surface, the risk is mitigated by the highly structured instructions and the lack of instructions that would lead to the execution of input-embedded commands.
- [EXTERNAL_DOWNLOADS]: The skill references local files (e.g., de_ai_phrase_library.md) for its logic. These are stored within the skill's reference directory and do not involve remote fetching of untrusted content.
Audit Metadata