dr-anomalies-report
Detect data anomalies and generate a comprehensive data-quality Excel WORKBOOK from Finance OS tables, computed over the table's ALL-TIME history (use the anomalies skill for a chat-only answer scoped to the latest fiscal year — the two baselines differ by design, so counts won't match). The MCP tools return baseline aggregates only; this skill derives findings, severity buckets, and the Data Quality Score client-side, then writes a multi-sheet workbook. Self-contained — pass --table-id to target a table directly, or it discovers the financials table on its own; no profile or setup step required.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
SKILL.md describes that /dr-anomalies-report reads table data and schema via MCP tools (e.g., list_data_models, list_aliased_fields/get_fields_by_id, profile_numeric_fields/profile_categorical_fields, start_distinct_values_by_*/start_aggregation_by_*) and then fetches sample records via get_data_by_alias/get_data_by_id based on discovered IDs, meaning outsider-authored free text can be ingested if an outsider can submit data into those fields.
- Repository
- Datarails/dr-claude-code-plugins-re
- Commit
0a038a3
- 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.