testland/bug-report-template
Builds a well-formed bug (defect) report from raw observation notes - fills in summary, environment, steps to reproduce, expected vs actual, and severity rationale - and validates that each field has the load-bearing content reviewers and engineers need to triage. Also converts a single test-failure record (JUnit XML, Allure JSON, pytest log, Playwright report) into a classified, ready-to-file bug spec, and provides the adversarial review checklist that gates a report before it enters the tracker (required fields, single-description title test, severity-priority independence, reproduction quality). Use when a stakeholder reports a problem informally, when a CI failure artefact needs to become a triageable report, or when a drafted report needs a pre-filing quality audit.
81
95%
Does it follow best practices?
Impact
80%
0.88xAverage score across 10 eval scenarios
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs extracting and pasting verbatim error messages, stack traces, and logs into the bug report (Actual field), which can cause the LLM to output sensitive secrets or tokens contained in those artifacts.
Where we found it
[REDACTED]
secret · 10 sites
The plugin explicitly instructs the agent to extract and output verbatim error messages, stack traces, and logs into the bug report's Actual field and spec template, which could expose secrets/tokens embedded in those artifacts.
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 a workflow that takes raw outsider-authored text from a chat message/voice memo/copy-pasted error at runtime (Step 1: “From the input…extract…verbatim error messages…exact UI surface…environment details…expected vs actual”), then uses it to populate the bug report template.
Where we found it
raw user input (chat message, voice memo, copy-pasted error, error log, screenshot caption)
content-type · 5 sites
The plugin ingests raw outsider-authored text (chat messages, voice memos, copy-pasted errors, error logs) and processes it to populate bug report fields, exposing the LLM to indirect prompt injection from adversarial content in those inputs.
SKILL.md
35
The skill is a workflow that takes raw input (a chat message, a voice
SKILL.md
36
memo transcription, a copy-pasted error) and produces a filled
SKILL.md
69
From the input (chat message, error log, screenshot caption, voice
SKILL.md
54
Extract verbatim errors, the UI surface, environment details, and the
SKILL.md
55
reporter's expected-vs-actual from the raw input (Step 1); flag any gap
CI failure records (JUnit XML, Allure JSON, pytest log, Playwright HTML, TestNG XML)
content-type · 6 sites
The plugin ingests CI failure records in multiple structured formats, which contain error messages and stack traces that could include attacker-controlled content (e.g., from malicious test inputs or responses), exposing the LLM to indirect prompt injection.
- Audited
- Security analysis