flaky-detector
Detect flaky tests from CI history and propose LLM-validated fixes via quarantine pull requests. Use to find flaky tests, analyze CI test stability, identify tests that flip pass/fail without code changes, or set up automated quarantine workflows. Supports any test framework that emits JUnit XML (pytest, unittest, JUnit, TestNG, Vitest, Jest with junit reporter). Trigger when users mention "flaky tests", "intermittent failures", "tests that randomly fail", "quarantine flaky tests", "CI flakiness", or ask to "find unreliable tests", "analyze CI history", "mark tests as flaky".
92
100%
Does it follow best practices?
Impact
95%
2.11xAverage score across 2 eval scenarios
Low
Low-risk findings worth noting
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 runtime path `src/flaky_detector/parser.py` (`parse_junit_xml` / `parse_directory`) ingests outsider-authored free text from user-supplied JUnit XML files (`--input` directory/file), including `<failure message>` / `<error message>` contents that are then carried into the LLM prompt via `src/flaky_detector/agent.py` (`_pick_failure_message` → `DEFAULT_PROMPT_TEMPLATE`).
- Repository
- golikovichev/flaky-detector-agent
- Path
SKILL.md
- Commit
1f7aa1a
- 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.