dr-anomalies
Detect data anomalies in one Datarails Finance OS table and answer IN CHAT — severity-ranked outliers, duplicates, missing/null rates, rare values — scoped to the latest complete fiscal year. Writes no file (use the anomalies-report skill for an Excel workbook; use the profile skill for unscoped whole-history statistics). The MCP profiling and aggregation tools return baseline aggregates only (raw rows come from the separate get_data_by_* calls); this skill computes the findings client-side.
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 skill reads data rows and aggregates from Datarails Finance OS tables via MCP tools, which can contain user-submitted finance and transaction data.
- Repository
- Datarails/dr-claude-code-plugins-re
- Commit
3fb5a24
- 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.