ieee-writing-materials
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The analyzed files consist entirely of markdown documentation, JSON inventory lists, and TSV data tables containing academic writing examples (openers, transitions, hedge verbs) and stylistic rules.
- [NO_CODE]: The skill does not contain any executable scripts or binary files in the provided contents. While external Python scripts are mentioned in the documentation for maintenance purposes, they are not included in the skill's operational context, and the core functionality relies on data retrieval.
- [DATA_RELIABILITY]: The content is derived from a filtered corpus of 353 IEEE publications, with clear provenance provided in the knowledge metadata. The skill uses a 'core' vs 'candidate' promotion system for rules, indicating a high level of curation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests text from third-party academic papers. While this represents a theoretical injection surface, the risk is mitigated by the structured format (TSV) and the specific academic nature of the content. There are no dangerous capabilities within the skill's instructions that would allow for exploitation via this data.
Audit Metadata