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 go-security-pitfallsgit 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/go-security-pitfalls)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/go-security-pitfalls"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/go-security-pitfalls/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/go-security-pitfalls"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/go-security-pitfalls.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 | $0.00046 | $0.01614 |
| Opus 5.5 | $0.00018 | $0.00646 |
| Sonnet 5.5 | $0.00009 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
go-security-pitfalls 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Security Pitfalls
Overview
Go removes whole classes of bugs (memory safety, implicit shell, unsafe default deserialization), which makes the remaining ones look innocent: a fmt.Sprintf in a query builder, a HasPrefix path check, a template.HTML conversion. Memory-safety findings in pure Go are excluded; unsafe and cgo are the exception.
1. SQL: database/sql, sqlx, GORM (CWE-89)
// ❌
db.QueryContext(ctx, fmt.Sprintf("SELECT * FROM tasks WHERE owner = '%s'", owner))
// ✅
db.QueryContext(ctx, "SELECT * FROM tasks WHERE owner = $1", owner)
GORM accepts raw SQL in more places than people expect:
// ❌ all of these take SQL text
db.Where(fmt.Sprintf("name = '%s'", name)).Find(&users)
db.Order(r.URL.Query().Get("sort")).Find(&users) // ORDER BY injection
db.First(&user, r.PathValue("id")) // a string id is used as an inline condition
db.Raw("SELECT … " + filter).Scan(&rows)
// ✅
db.Where("name = ?", name).Find(&users)
db.Order(clause.OrderByColumn{Column: clause.Column{Name: sortCols[key]}}).Find(&users)
db.First(&user, "id = ?", id)
2. Commands: os/exec (CWE-78, CWE-88)
exec.Command never invokes a shell — unless you pass sh -c. With separate args the risk is argument injection:
// ❌ shell
exec.Command("sh", "-c", "git clone "+repoURL).Run()
// ❌ no shell, but repoURL = "--upload-pack=…" is an option
exec.Command("git", "clone", repoURL, dir).Run()
// ✅
exec.Command("git", "clone", "--", repoURL, dir).Run()
Also check cmd.Env built from request data (NODE_OPTIONS, LD_PRELOAD, GIT_SSH_COMMAND — injection-and-dangerous-sinks).
3. Paths: filepath, os.Root (CWE-22)
// ❌ lexical check: a symlink inside base escapes it, and
// "/srv/data-other/x" passes HasPrefix(p, "/srv/data")
p := filepath.Join(base, name)
if !strings.HasPrefix(p, base) { … }
// ✅ Go 1.24+: lookups confined to the root, symlinks included
root, err := os.OpenRoot(base)
f, err := root.Open(name)
// ✅ older Go: reject anything non-local before joining
if !filepath.IsLocal(name) { return errBadPath }
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 · 125 lines · 46 tokens per session scan A d40cc5a7c484
go-security-pitfalls is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 1,614 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
cuopt-routing-api-python
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
mcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
hns-moaiadk-best-practices
Every change must pass all five dimensions before completion.