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 xalgorix/xalgorix --skill performing-cloud-penetration-testing-with-pacugit clone --depth 1 https://github.com/xalgorix/xalgorixWrote 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/xalgorix/xalgorix/performing-cloud-penetration-testing-with-pacu)<a href="https://agentmods.dev/skills/xalgorix/xalgorix/performing-cloud-penetration-testing-with-pacu"><img src="https://agentmods.dev/badge/skills/xalgorix/xalgorix/performing-cloud-penetration-testing-with-pacu/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/xalgorix/xalgorix/performing-cloud-penetration-testing-with-pacu"><img src="https://agentmods.dev/badge/skills/xalgorix/xalgorix/performing-cloud-penetration-testing-with-pacu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Privilege Escalation · line 256 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00051 | $0.03039 |
| Opus 5 | $0.00026 | $0.01520 |
| Sonnet 5 | $0.00010 | $0.00608 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade A, and why
performing-cloud-penetration-testing-with-pacu scanned grade A with 0 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 7d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performing Cloud Penetration Testing with Pacu
When to Use
- When conducting authorized penetration testing of AWS environments
- When validating the effectiveness of IAM policies, SCPs, and permission boundaries
- When assessing the blast radius of a compromised set of AWS credentials
- When testing detection capabilities of GuardDuty, Security Hub, and custom alerting
- When building red team exercises against AWS cloud infrastructure
Do not use for unauthorized testing of any AWS account, for testing AWS infrastructure itself (covered by shared responsibility), for DDoS or volumetric attacks without AWS approval, or for production account testing without explicit authorization and breakglass procedures.
Most Often Missed & How to Confirm
- Incomplete enumeration hides escalation paths:
iam__privesc_scanonly reasons over permissions Pacu already collected. Runiam__enum_permissionsfirst and watch forAccessDeniedoniam:GetAccountAuthorizationDetails- a gap there makes the scanner report "no privesc" when paths exist. - Region scoping: Pacu enumerates only regions in
set_regions. Runset_regions allor you'll silently miss EC2, Lambda, Secrets Manager, and SSM resources living in us-west-2 / eu-* etc. - PassRole combos are the high-value misses:
iam:PassRole+lambda:CreateFunction,ec2:RunInstances,glue:CreateDevEndpoint, orcloudformation:CreateStack. These fail silently ifiam__enum_rolesdidn't map the passable target roles first. - Don't stop at IAM:
lambda__enum(env vars),ssm__download_parameters, andsecretsmanager__enumroutinely yield the next credential set. Also check unauth paths:ebs__enum_snapshots_unauthand public AMIs/RDS snapshots shared with your account. - Resource-policy backdoors: S3 bucket policies, KMS key policies, SQS, and Lambda resource policies can grant access the IAM scan never sees.
How to confirm a hit (avoid false negatives): after iam__privesc_scan --escalate, prove the new access - run aws sts get-caller-identity with the escalated creds and actually perform the gated action (e.g. attach a policy then list-attached-user-policies, or invoke the created Lambda and read its output). A 200 from CreateFunction is not proof of admin. Don't conclude "no escalation" until: iam__enum_permissions completed with no AccessDenied gaps, all regions were scanned, PassRole targets were mapped, and resource-based policies were reviewed.
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.
- 7d ago First seen · 310 lines · 51 tokens per session scan A 5989435f24b1
performing-cloud-penetration-testing-with-pacu is a skill published in the GitHub repository xalgorix/xalgorix (971 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 3,039 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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.
auditing-aws-s3-bucket-permissions
Systematically audit AWS S3 bucket permissions to identify publicly accessible buckets, overly permissive ACLs, misconfigured bucket policies, and missing encryption settings using AWS CLI, S3audit, and Prowler to enforce least-privilege data access controls.
analyzing-azure-activity-logs-for-threats
Queries Azure Monitor activity logs and sign-in logs via azure-monitor-query to detect suspicious administrative operations, impossible travel, privilege escalation, and resource modifications. Builds KQL queries for threat hunting in Azure environments. Use when investigating suspicious Azure tenant activity or…
cors-chain-automation
Use when a bounded list of authorized API endpoints needs consistent CORS triage before browser validation.
humanize-automation
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
cloud-iam-deep
GCP/AWS/Azure cloud exploitation -- Cloud Functions, Firestore, Cloud Run, S3, MinIO, Blob Storage, SA keys.