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 web2-recongit 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/web2-recon)<a href="https://agentmods.dev/skills/uphiago/recon-skills/web2-recon"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/web2-recon/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/uphiago/recon-skills/web2-recon"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/web2-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 YARA Match · line 315 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Supply Chain · line 388 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 403 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 Privilege Escalation · line 427 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.
- medium Rogue Agent · line 22 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 29 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 315 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 325 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 332 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.
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 | $0.00103 | $0.07194 |
| Opus 5 | $0.00051 | $0.03597 |
| Sonnet 5 | $0.00021 | $0.01439 |
| Haiku 4.5 | $0.00010 | $0.00719 |
Grade C, and why
web2-recon scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --max-time 30 --connect-timeout 10 -sk "https://$TARGET/static/js/main.*.js" 2>/dev/null | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --max-time 30 --connect-timeout 10 -s "https://crt.sh/?q=%.${TARGET}&output=json" \ How it starts
The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WEB2 RECON PIPELINE
Full asset discovery from nothing to a prioritized URL list ready for hunting.
SETUP (one-time)
# 1. Set your Chaos API key (get free key at chaos.projectdiscovery.io)
export CHAOS_API_KEY="your-key-here"
# Add to ~/.zshrc or ~/.bashrc for persistence:
echo 'export CHAOS_API_KEY="your-key-here"' >> ~/.zshrc
# 2. Update nuclei templates (run weekly)
nuclei -update-templates
# 3. Configure subfinder with API keys for more sources
mkdir -p ~/.config/subfinder
cat > ~/.config/subfinder/config.yaml << 'EOF'
# Get free keys at: virustotal.com, securitytrails.com, censys.io, shodan.io
virustotal: [YOUR_VT_KEY]
securitytrails: [YOUR_ST_KEY]
censys_apiid: YOUR_CENSYS_ID
censys_secret: YOUR_CENSYS_SECRET
shodan: [YOUR_SHODAN_KEY]
EOF
# 4. Verify alltools installed
which subfinder httpx dnsx nuclei katana waybackurls gau dalfox ffuf anew gf interactsh-client
THE 5-MINUTE RULE
If a target shows nothing interesting after 5 minutes of recon, move on. Don't burn hours on dead surface.
5-minute kill signals:
- All subdomains return 403 or static marketing pages
- No API endpoints visible in URLs
- No JavaScript bundles with interesting endpoint paths
- nuclei returns 0 medium/high findings
- No forms, no authentication, no user data
STANDARD RECON PIPELINE
Pre-Hunt: Always Run First
TARGET="target.com"
# Step 0: Passive — crt.sh certificate transparency (no API key needed)
curl --max-time 30 --connect-timeout 10 -s "https://crt.sh/?q=%.${TARGET}&output=json" \
| jq -r '.[].name_value' \
| sed 's/\*\.//g' \
| sort -u > /tmp/subs.txt
echo "[+] crt.sh: $(wc -l < /tmp/subs.txt) subdomains"
# Step 1: Chaos API (ProjectDiscovery — most comprehensive source)
curl --max-time 30 --connect-timeout 10 -s "https://dns.projectdiscovery.io/dns/$TARGET/subdomains" \
-H "Authorization: $CHAOS_API_KEY" \
| jq -r '.[]' >> /tmp/subs.txt
echo "[+] Chaos returned $(wc -l < /tmp/subs.txt) subdomains"
# Step 2: subfinder (passive multi-source)
subfinder -d $TARGET -silent | anew /tmp/subs.txt
assetfinder --subs-only $TARGET | anew /tmp/subs.txt
echo "[+] Total subdomains after all sources: $(wc -l < /tmp/subs.txt)"
# Step 3: DNS resolution + live host check
cat /tmp/subs.txt | dnsx -silent | httpx -silent -status-code -title -tech-detect | tee /tmp/live.txt
echo "[+] Live hosts: $(wc -l < /tmp/live.txt)"
# Step 4: URL crawl
cat /tmp/live.txt | awk '{print $1}' | katana -d 3 -jc -kf all -silent | anew /tmp/urls.txt
# Step 5: Historical URLs
echo $TARGET | waybackurls | anew /tmp/urls.txt
gau $TARGET --subs | anew /tmp/urls.txt
echo "[+] Total URLs: $(wc -l < /tmp/urls.txt)"
# Step 6: Nuclei scan
nuclei -l /tmp/live.txt -t ~/nuclei-templates/ -severity critical,high,medium -o /tmp/nuclei.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.
- 8d ago First seen · 714 lines · 103 tokens per session scan C af6c4dda80a0
web2-recon is a skill published in the GitHub repository uphiago/recon-skills (1,254 stars, last pushed 10d ago), licensed MIT. It adds 103 tokens to every session and 7,194 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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.
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-aws-config-rules-for-compliance
Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.
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.
implementing-cloud-trail-log-analysis
Implementing AWS CloudTrail log analysis for security monitoring, threat detection, and forensic investigation using Athena, CloudWatch Logs Insights, and SIEM integration to identify unauthorized access, privilege escalation, and suspicious API activity.
implementing-zero-trust-network-access
Implementing Zero Trust Network Access (ZTNA) in cloud environments by configuring identity-aware proxies, micro-segmentation, continuous verification with conditional access policies, and replacing traditional VPN-based access with BeyondCorp-style architectures across AWS, Azure, and GCP.