Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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 PurpleAILAB/Decepticon --skill sql-injectiongit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/purpleailab/decepticon/sql-injection)<a href="https://agentmods.dev/skills/purpleailab/decepticon/sql-injection"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/sql-injection/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/purpleailab/decepticon/sql-injection"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/sql-injection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.01360 |
| Opus 5.5 | $0.00019 | $0.00544 |
| Sonnet 5.5 | $0.00009 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
sql-injection scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://target.com/search?q=1' AND SLEEP(5)-- -" Copies of this mod
1 near-identical copy found in the catalogue:
- sql-injection — 92% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Injection Hunting Playbook
Classic, still the king. Modern ORMs reduce the surface area but every codebase has escape hatches (raw queries, dynamic table names, LIKE fragments) where taint tracking pays off.
1. Sources
Anything accepting untrusted input: query params, form bodies, headers, cookies, JWT claims, file contents parsed as config, message-queue payloads.
2. Sinks by language/framework
| Language | Safe API | Dangerous API |
|---|---|---|
| Python | cursor.execute(sql, params) |
cursor.execute(f"... {user}"), %-format |
| Python | SQLAlchemy text().bindparams |
text(f"... {user}"), raw_sql |
| Python | Django ORM filter kwargs | Model.objects.raw(...), .extra(where=[...]) |
| Node | pg.query(text, params) |
Template literals with user data |
| Node | Prisma $queryRaw\...`` |
$queryRawUnsafe(userString) |
| Java | PreparedStatement |
Statement.executeQuery(string + user) |
| Java | JPA criteria | entityManager.createNativeQuery(user + sql) |
| Go | db.Query(text, args...) |
fmt.Sprintf → db.Query |
| Ruby | Rails where("col = ?", x) |
where("col = '#{x}'"), find_by_sql(interp) |
| PHP | PDO prepared | mysqli_query($conn, $user . $sql) |
3. Taint audit steps
# Semgrep covers 80% of obvious cases
semgrep --config p/sql-injection /workspace/src --sarif -o /workspace/sem-sqli.sarif
kg_ingest_sarif("/workspace/sem-sqli.sarif", "semgrep")
# Grep for the high-signal patterns semgrep misses (dynamic order/group by)
grep -rE 'ORDER BY.*\$|LIMIT.*\$|GROUP BY.*\$' /workspace/src
grep -rE 'execute\s*\(.*f["\']|execute\s*\(.*%.*%' /workspace/src
# Django raw + extra (scanner blind spot)
grep -rE '\.raw\(|\.extra\(' /workspace/src
# Second-order: anything that stores user input then queries by it unescaped
grep -rE 'INSERT INTO.*VALUES.*\?|UPDATE.*SET' /workspace/src
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.
- 2mo ago First seen · 118 lines · 47 tokens per session scan A 87731fd4aace
sql-injection is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,504 stars, last pushed 8d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,360 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
sql-injection compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sql-injectionPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 47 | Claude Code, Codex |
| optimizing-ef-core-queriesHarmeet10000/skills | Skill | 7 | 6mo ago | MIT | A | 53 | Claude Code, Codex |
| golang-databaseHarmeet10000/skills | Skill | 7 | 6mo ago | MIT | A | 116 | Claude Code |
| postgresql-table-designHarmeet10000/skills | Skill | 7 | 6mo ago | MIT | A | 31 | Claude Code, Codex |
| sql-optimization-patternsHarmeet10000/skills | Skill | 7 | 6mo ago | MIT | A | 44 | Claude Code, Codex |
| query-writinglangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| triage-issuesgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 164 | Claude Code, Codex |