cekura-bot-test-writer
Use when a pull request changes a voice agent and the repository's committed Cekura test suite has to keep up: "update the tests for this PR", "extend test coverage for these changes", "does this PR need new voice tests", "keep cekura.tests.json in sync", "add a regression test for this bug fix", "review the suite against my diff", "run a test writer on every PR". Reads the PR diff against its merge base, decides per change whether existing cases already cover it, and makes the smallest edit that closes a real gap — most often no edit at all. This skill updates an existing suite; it never creates one from scratch (use cekura-infra-test-suite), never authors dashboard evaluators (use cekura-eval-design), and never places a live call.
77
97%
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 required workflow runs on pull requests (`pull_request` trigger) and reads PR diffs and repository files, ingesting outsider-authored free text from GitHub pull requests.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill references `https://docs.cekura.ai/mcp/overview` and uses `npx --yes skills add cekura-ai/cekura-skills --skill cekura-bot-test-writer` and `uses: cekura-ai/cekura-github-actions/run-suite@v1.3.0` which fetch external packages and content at setup/runtime without explicit enforcement of signatures, digests, or immutable identifiers, making them weak/unknown third-party dependencies.
- Repository
cekura-ai/cekura-skills
- Revision
523fe2c
- 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.