review-ci
Review CI results for the current branch, commit, or PR using the Datadog MCP. Use this when CI is failing, to understand what's blocking a PR, or to get actionable fix instructions for failed jobs and tests.
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
The skill explicitly fetches and ingests external CI/log/test data from third-party services (Datadog via search_datadog_logs/search_datadog_ci_pipeline_events/search_datadog_test_events and GitHub via gh run list/view) and instructs the agent to read and act on those logs/results to determine root causes and fixes, which could contain untrusted user-generated content that materially influences actions.
- Repository
- DataDog/dd-trace-py
- Commit
5fe261d
- 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.