semantic-relations
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes links to foundational grounding sources from trusted academic and standardization organizations, such as Princeton University (WordNet), the World Wide Web Consortium (W3C for SKOS and OWL), and ICSI/Berkeley (FrameNet).
- [EXTERNAL_DOWNLOADS]: Metadata within the skill references the author's public repository on GitHub (
github.com/jacob-balslev/skill-graph) for context within the broader Skill Graph project. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and type user-provided strings (concept names, identifier labels). While it processes untrusted input, the skill's execution environment is limited by its configuration to non-destructive tools ('Read', 'Grep'), and it does not perform network operations or shell execution that could be exploited through data ingestion.
Audit Metadata