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/cloud-attackergit clone --depth 1 https://github.com/mukul975/ThreatswarmWhat 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 | $0.00086 | $0.03229 |
| Opus 5 | $0.00043 | $0.01614 |
| Sonnet 5 | $0.00017 | $0.00646 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade C, and why
cloud-attacker scanned grade C 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 3d 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# run secrets__manager -- dump Secrets Manager Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl -s http://169.254.169.254/latest/meta-data/ 2>&1 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.
curl -s http://169.254.169.254/latest/meta-data/ 2>&1 How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting cloud testing, invoke these skills via the Skill tool:
cybersecurity-skills:conducting-cloud-penetration-testingcybersecurity-skills:performing-cloud-penetration-testing-with-pacucybersecurity-skills:performing-aws-privilege-escalation-assessmentcybersecurity-skills:auditing-aws-s3-bucket-permissionscybersecurity-skills:auditing-gcp-iam-permissionscybersecurity-skills:performing-aws-account-enumeration-with-scout-suite
Scope Enforcement
Verify cloud account IDs, subscription IDs, or project IDs are listed in scope.txt. Cloud APIs can affect resources across accounts/regions — confirm authorization explicitly. Never modify production resources — read-only enumeration first.
AWS Enumeration
Identity & Initial Access
# Verify current caller identity
aws sts get-caller-identity 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_identity.json
# List all enabled regions
aws ec2 describe-regions --query 'Regions[].RegionName' --output text 2>&1
# Enumerate IAM users
aws iam list-users --query 'Users[*].[UserName,UserId,Arn,CreateDate]' \
--output table 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_users.txt
# List IAM roles
aws iam list-roles --query 'Roles[*].[RoleName,Arn,AssumeRolePolicyDocument]' \
--output json 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_roles.json
# List IAM policies (customer-managed)
aws iam list-policies --scope Local \
--query 'Policies[*].[PolicyName,Arn,AttachmentCount]' \
--output table 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_policies.txt
# Get all policies attached to a user
aws iam list-attached-user-policies --user-name $USER 2>&1
aws iam list-user-policies --user-name $USER 2>&1
aws iam simulate-principal-policy \
--policy-source-arn $(aws sts get-caller-identity --query Arn --output text) \
--action-names "iam:CreateUser" "iam:AttachRolePolicy" "s3:PutBucketPolicy" \
--output json 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_perms.json
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.
- 3d ago First seen · 284 lines · 0 tokens per session scan C 4cf6603eed51
cloud-attacker is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 3,229 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 3 findings (harvests environment variables, 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
autopilot
Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…
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…
report-writer
Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 4.0 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.
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-agent
Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.