Recon Skills is a pack of security-testing skills covering reconnaissance, web applications, APIs, authentication, vulnerability validation, cloud infrastructure, and reporting. Security professionals use it for authorized assessments of systems they own or have written permission to test. The catalogue entries are individual skills from the pack.
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 uphiago/recon-skills --skill deep-invadegit clone --depth 1 https://github.com/uphiago/recon-skillsWrote 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/uphiago/recon-skills/deep-invade)<a href="https://agentmods.dev/skills/uphiago/recon-skills/deep-invade"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/deep-invade.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 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 Supply Chain · line 318 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 341 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high YARA Match · line 362 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 80 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.
- medium Data Exfiltration · line 94 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.
- medium Data Exfiltration · line 108 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.
- medium Data Exfiltration · line 318 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.
- medium Privilege Escalation · line 403 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00024 | $0.05781 |
| Opus 5 | $0.00012 | $0.02891 |
| Sonnet 5 | $0.00005 | $0.01156 |
| Haiku 4.5 | $0.00002 | $0.00578 |
Grade C, and why
deep-invade scanned grade C with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# Extract API keys Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo systemctl start tor Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --max-time 30 --connect-timeout 10 -sk "https://$TARGET/wp-json/wc/v3/" | python3 -c " 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.
compatibility: Requires curl, nmap, python3, httpx, nuclei How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Invade Skill
Focused follow-up methodology for WordPress targets prioritized by
wp-mass-recon. It connects XML-RPC SSRF validation, exposed-log analysis,
plugin version review, JavaScript inspection, staging discovery, service
mapping, and API enumeration.
When to Use
wp-mass-reconscored a target >= 6 (CORS confirmed, XMLRPC open, source leaks found).- You are assigned a single high-value target for deep assessment.
- After surface recon, you need to find the chain that leads to RCE or data breach.
- Multiple independent signals justify a deeper, target-specific follow-up.
Prerequisites
curl,python3, and the tools required by each selected phase.- Target already scored >= 6 from wp-mass-recon (WordPress confirmed, at least 2 of: CORS/XMLRPC/source leak).
- Collaborator endpoint (Burp Collaborator, interactsh, or your own server) for SSRF/blind confirmation.
nmapavailable when port scanning is in scope.
How to Run
Execute probes in order. Each phase builds on the previous:
- Extended SSRF probe (XMLRPC pingback to IMDS, localhost, internal IPs)
- Error log mining (fetch and grep for creds, paths, SQL)
- Plugin CVE matrix (30+ REST namespaces, readme.txt versions)
- JavaScript bundle analysis (11 regex patterns for secrets)
- Subdomain/staging enumeration (crt.sh, httpx, WP install pages)
- Port scan (nmap -F for MySQL, FTP, SSH, internal APIs)
- API discovery (Swagger, GraphQL, WooCommerce, Gravity Forms)
Quick Reference
| Phase | Technique | Tool | Typical time |
|---|---|---|---|
| 1 | XML-RPC SSRF validation with an authorized callback | curl + callback service | 2 min |
| 2 | Exposed error-log analysis | Python regex | 1 min |
| 3 | Plugin namespace and version review | curl + regex | 3 min |
| 4 | JavaScript bundle analysis | js-secrets-extraction |
2 min |
| 5 | Subdomain and staging comparison | crt.sh, httpx, curl | 5 min |
| 6 | Scoped port and service discovery | nmap | scope dependent |
| 7 | API description and route discovery | curl + regex | 2 min |
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.
- 8d ago First seen · 458 lines · 24 tokens per session scan C ec4e4ef9926d
deep-invade is a skill published in the GitHub repository uphiago/recon-skills (1,247 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 5,781 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 4 findings (harvests environment variables, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
detecting-compromised-cloud-credentials
Detecting compromised cloud credentials across AWS, Azure, and GCP by analyzing anomalous API activity, impossible travel patterns, unauthorized resource provisioning, and credential abuse indicators using GuardDuty, Defender for Identity, and SCC Event Threat Detection.
implementing-cloud-dlp-for-data-protection
Implementing Cloud Data Loss Prevention (DLP) using Amazon Macie, Azure Information Protection, and Google Cloud DLP API to discover, classify, and protect sensitive data across cloud storage, databases, and data pipelines.
securing-api-gateway-with-aws-waf
Securing API Gateway endpoints with AWS WAF by configuring managed rule groups for OWASP Top 10 protection, creating custom rate limiting rules, implementing bot control, setting up IP reputation filtering, and monitoring WAF metrics for security effectiveness.
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.
auditing-azure-active-directory-configuration
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
auditing-gcp-iam-permissions
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.