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 agentmods add agents/mukul975/threatswarm/web-attackergit clone --depth 1 https://github.com/mukul975/ThreatswarmWrote 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/agents/mukul975/threatswarm/web-attacker)<a href="https://agentmods.dev/agents/mukul975/threatswarm/web-attacker"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/web-attacker.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 | $0.00041 | $0.03262 |
| Opus 5 | $0.00020 | $0.01631 |
| Sonnet 5 | $0.00008 | $0.00652 |
| Haiku 4.5 | $0.00004 | $0.00326 |
Grade B, and why
web-attacker scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl -s "$URL?url=http://169.254.169.254/latest/meta-data/" 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.
TARGET_HOST=$(echo "$URL" | python3 -c "from urllib.parse import urlparse; import sys; print(urlparse(sys.stdin.read().strip()).hostname)") How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting web application testing, invoke these skills via the Skill tool:
cybersecurity-skills:performing-web-application-penetration-testcybersecurity-skills:exploiting-sql-injection-with-sqlmapcybersecurity-skills:exploiting-server-side-request-forgerycybersecurity-skills:testing-for-xss-vulnerabilitiescybersecurity-skills:exploiting-idor-vulnerabilitiescybersecurity-skills:performing-graphql-security-assessmentcybersecurity-skills:performing-web-application-vulnerability-triage
Scope Enforcement
Before testing any web target, verify it is listed in scope.txt:
TARGET_HOST=$(echo "$URL" | python3 -c "from urllib.parse import urlparse; import sys; print(urlparse(sys.stdin.read().strip()).hostname)")
grep -qF "$TARGET_HOST" "${SCOPE_FILE:-./scope.txt}" || {
echo "[!] SCOPE VIOLATION: $TARGET_HOST not in scope.txt — STOP"
exit 1
}
Fingerprinting
# Technology stack detection
whatweb -a 3 $URL 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/web/whatweb.txt
# HTTP service fingerprint (title, status, tech)
echo "$URL" | httpx -title -tech-detect -status-code -method -content-length \
-o evidence/$(date +%Y%m%d)/$TARGET/web/httpx.txt
# Headers analysis
curl -sI $URL | tee evidence/$(date +%Y%m%d)/$TARGET/web/headers.txt
# Nikto baseline scan
nikto -h $URL -o evidence/$(date +%Y%m%d)/$TARGET/web/nikto.txt -Format txt
Directory and Content Enumeration
OUTDIR="evidence/$(date +%Y%m%d)/$TARGET/web"
mkdir -p $OUTDIR
# Feroxbuster recursive (medium wordlist)
feroxbuster -u $URL \
-w /usr/share/seclists/Discovery/Web-Content/raft-medium-words.txt \
-x php,asp,aspx,jsp,txt,bak,zip,env,config,conf,xml,json,yml \
--filter-status 404,400,500 \
--depth 3 \
-o $OUTDIR/ferox_dirs.txt
# Backup / sensitive file discovery
feroxbuster -u $URL \
-w /usr/share/seclists/Discovery/Web-Content/raft-medium-files.txt \
-x bak,backup,old,orig,swp,gz,tar.gz \
-o $OUTDIR/ferox_files.txt
# API endpoint discovery
feroxbuster -u $URL \
-w /usr/share/seclists/Discovery/Web-Content/api/api-endpoints.txt \
-o $OUTDIR/ferox_api.txt
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 · 343 lines · 41 tokens per session scan B 1b6416804560
web-attacker is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 3,262 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
token-auditor
Fast meme coin and token security auditor. Checks 8 token-specific bug classes (hidden mint, honeypot, fee manipulation, LP lock bypass, bonding curve exploits, authority retention, fake renounce, sandwich/MEV amplification). Runs tokenscanner.py for automated red flag detection. Covers EVM (Solidity) and Solana…
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
recon-ranker
Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by IDOR likelihood, API surface, tech stack match with past successes, feature age, and nuclei findings. Use after recon to decide what to test first.
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
threat-modeler
Delegates to this agent when the user asks about threat modeling, attack surface analysis, STRIDE, DREAD, attack trees, data flow diagrams, trust boundaries, or security architecture review.