infer-ontology
Infer a semantic ontology from all files in the working directory - entities, attributes, relationships, domain taxonomy, and cross-file join paths. Outputs ONTOLOGY.md.
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs the agent to read file contents and include data previews, frequency distributions, controlled vocabularies and data-dictionary fields in the generated ONTOLOGY.md, so any secrets present in those files would be extracted and embedded verbatim in the output.
- Repository
- dathere/qsv
- Commit
e5a3bdc
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.