testland/manual-test-script-author
Builds stakeholder-readable scripted manual test cases from a feature spec in four formats: a step-table (preconditions / steps / expected result / actual / pass-fail / notes) for spreadsheet review, a Gherkin Given/When/Then format for BDD-aware teams, a business-language UAT script with acceptance-criteria mapping and contractual sign-off (references/uat-format.md), and a one-line-per-item execution checklist for smoke / on-call / bug-bash / compliance sweeps (references/checklist-format.md). Each script is self-contained (no implicit team knowledge), single-scenario (one happy + N edge per script), and includes the data setup the tester needs without being a developer. Use when a feature can't be (or shouldn't be) fully automated and a human tester needs an executable script or checklist - UAT sign-off rounds, regression baselines, certification testing, deploy smoke checklists, exploratory follow-up scripts.
94
88%
Does it follow best practices?
Impact
95%
0.98xAverage 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 requires scripts to "specify" test account credentials (and lists concrete test-account data), which forces the LLM to emit credential values verbatim in generated test scripts, creating an exfiltration risk.
Where we found it
[REDACTED]
secret · 14 sites
The skill's Step 5 explicitly instructs the agent that generated test scripts "must specify: [REDACTED]", and all example output templates demonstrate emitting account emails, passwords, and payment card numbers verbatim in the generated output, teaching the LLM to emit real credentials when substituted.
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 required runtime workflow ingests a user-provided “feature spec” at Step 1 (“user story / PRD section”, “bug report”, “exploratory testing session debrief”, or “acceptance criterion line item”) and then formats/rewrites it into test scripts, so outsider free text can be submitted as that input.
Where we found it
user-provided feature spec (user story / PRD section / bug report / exploratory testing session debrief / acceptance criterion)
content-type · 5 sites
Step 1 of the skill ingests user-provided free-text documents (user stories, PRD sections, bug reports, session debriefs, acceptance criteria) and reformats them into test scripts, so the content is processed and acted upon by the LLM.
SKILL.md
47
The skill takes one of:
SKILL.md
49
- A user story / PRD section.
SKILL.md
50
- A bug report (for regression-baseline scripts).
SKILL.md
51
- An exploratory testing session debrief (for follow-up scripts).
SKILL.md
52
- An acceptance criterion line item (for UAT scripts).
- Audited
- Security analysis