prowler-ci

prowler-ci is a skill for Claude Code from prowler-cloud/prowler. It costs 67 tokens per session (802 once invoked), scanned A, original, Apache-2.0.

A guide for Prowler’s continuous integration (CI) checks, automated tests and rules that run on GitHub pull requests. It covers workflows for titles, changelogs, secrets, conflicts, labels, and code ownership.

In plain words
What is it for?
Use it to investigate failing PR checks, inspect GitHub Actions workflow conditions, validate titles and changelog entries, and understand automatic labels or review assignments.
Why use it?
It helps explain why a pull request check failed or why a workflow did not run for particular changed files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to investigate failing PR checks, inspect GitHub Actions workflow conditions, validate titles and changelog entries, and understand automatic labels or review assignments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prowler-cloud/prowler/prowler-ci
About the project

Prowler is an open-source cloud security platform that checks cloud environments for security issues and compliance with standards such as CIS, NIST, and GDPR. Security teams use it to assess configurations, prioritize findings, produce reports, and guide remediation.

prowler-cloud/prowler · 14,767 stars · on GitHub · prowler.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add prowler-cloud/prowler --skill prowler-ci
Clone the repo
git clone --depth 1 https://github.com/prowler-cloud/prowler

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prowler-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/prowler-cloud/prowler/prowler-ci.svg)](https://agentmods.dev/skills/prowler-cloud/prowler/prowler-ci)
Your own site
<a href="https://agentmods.dev/skills/prowler-cloud/prowler/prowler-ci"><img src="https://agentmods.dev/badge/skills/prowler-cloud/prowler/prowler-ci.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 37
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00802
Opus 5 $0.00034 $0.00401
Sonnet 5 $0.00013 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 8d ago against content hash 94ab1a76da74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prowler-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/prowler-ci/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What this skill covers

Use this skill whenever you are:

  • Reading or changing GitHub Actions workflows under .github/workflows/
  • Explaining why a PR fails checks (title, changelog, conflict markers, secret scanning)
  • Figuring out which workflows run for UI/API/SDK changes and why
  • Diagnosing path-filtering behavior (why a workflow did/didn't run)

Quick map (where to look)

  • PR template: .github/pull_request_template.md
  • PR title validation: .github/workflows/conventional-commit.yml
  • Changelog gate: .github/workflows/pr-check-changelog.yml (requires a fragment under <component>/changelog.d/)
  • Changelog compile (release time): .github/workflows/compile-changelogs.yml
  • Conflict markers check: .github/workflows/pr-conflict-checker.yml
  • Secret scanning: .github/workflows/find-secrets.yml
  • Auto labels: .github/workflows/labeler.yml and .github/labeler.yml
  • Review ownership: .github/CODEOWNERS

Debug checklist (PR failing checks)

  1. Identify which workflow/job is failing (name + file under .github/workflows/).
  2. Check path filters: is the workflow supposed to run for your changed files?
  3. If it's a title check: verify PR title matches Conventional Commits.
  4. If it's changelog: verify a valid fragment exists under the right <component>/changelog.d/ OR apply no-changelog label.
  5. If it's conflict checker: remove <<<<<<<, =======, >>>>>>> markers.
  6. If it's secrets (TruffleHog): see section below.

TruffleHog Secret Scanning

TruffleHog scans for leaked secrets. Common false positives in test files:

Patterns that trigger TruffleHog:

  • sk-*T3BlbkFJ* - OpenAI API keys
  • AKIA[A-Z0-9]{16} - AWS Access Keys
  • ghp_* / gho_* - GitHub tokens
  • Base64-encoded strings that look like credentials

Fix for test files:

# BAD - looks like real OpenAI key
api_key = "sk-test1234567890T3BlbkFJtest1234567890"

# GOOD - obviously fake
api_key = "sk-fake-test-key-for-unit-testing-only"

If TruffleHog flags a real secret:

  1. Remove the secret from the code immediately
  2. Rotate the credential (it's now in git history)
  3. Consider using .trufflehog-ignore for known false positives (rarely needed)

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 78 lines · 67 tokens per session scan A 94ab1a76da74

Subscribe to this mod's changes

prowler-ci is a skill published in the GitHub repository prowler-cloud/prowler (14,767 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 802 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.