live_database_ingest
Capture semantic-layer and knowledge updates from a live database schema snapshot.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow ingests JSON files from the work unit path `raw-sources/<connectionId>/live-database/<syncId>/` (e.g., the table JSON, `connection.json`, and `foreign-keys.json`), which are outsider-authored free text if the user can supply/upload raw files into that unit.
- Repository
Kaelio/ktx
- Revision
49a4ae6
- 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.