testland/test-run-summary-author
Use when a release note, status update or stand-up post needs a readable summary of one test run. Turns JUnit XML, Allure JSON or a TestRail, Xray or Zephyr export plus release context into a short narrative in markdown.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 ingests JUnit XML, Allure JSON, or test-management API exports from CI runners or test systems, which can contain outsider-authored test failure messages or assertions.
Where we found it
JUnit XML
content-type · 7 sites
The skill explicitly accepts JUnit XML files as input, which contain test failure messages, stack traces, and assertions authored by test writers (potentially outsiders), creating indirect prompt injection risk when the LLM processes this content.
Allure JSON
content-type · 4 sites
The skill explicitly accepts Allure results directories containing *-result.json and *-container.json files, which include test failure messages, stack traces, and assertions authored by test writers (potentially outsiders), creating indirect prompt injection risk.
SKILL.md
41
Allure results | Directory of *-result.json + *-container.json per https://allurereport.org/docs/ - Allure organises results by test status (passed / failed / broken / skipped / unknown), categories, and severity levels | allure-pytest, allure-jest, allure-junit5, allure-cucumber, etc.
SKILL.md
34
Ingest one of three input shapes:
SKILL.md
57
| Severity / category breakdown | Per Allure's severity and categories taxonomy when available; otherwise omitted | Risk-weighted reading of the same numbers |
SKILL.md
120
- Severity / categories require Allure or a test-management tool. JUnit XML alone does not carry severity; the skill cannot infer it from naming patterns.
Test-management API export (TestRail, Xray, Zephyr)
content-type · 4 sites
The skill explicitly accepts test-management API exports from TestRail, Xray, and Zephyr, which contain test failure messages, assertions, and comments authored by test writers (potentially outsiders), creating indirect prompt injection risk.
SKILL.md
42
Test-management API export | TestRail run export, Xray run export, Zephyr cycle export | Test-management integration skills
SKILL.md
34
Ingest one of three input shapes:
SKILL.md
57
| Severity / category breakdown | Per Allure's severity and categories taxonomy when available; otherwise omitted | Risk-weighted reading of the same numbers |
SKILL.md
120
- Severity / categories require Allure or a test-management tool. JUnit XML alone does not carry severity; the skill cannot infer it from naming patterns.
- Audited
- Security analysis