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 hunt-metrics-exposuregit 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/hunt-metrics-exposure)<a href="https://agentmods.dev/skills/uphiago/recon-skills/hunt-metrics-exposure"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/hunt-metrics-exposure/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/hunt-metrics-exposure"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/hunt-metrics-exposure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 65 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 66 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 67 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 70 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 71 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.
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 | $0.00029 | $0.01382 |
| Opus 5 | $0.00015 | $0.00691 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade C, and why
hunt-metrics-exposure scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/actuator/health" | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
code=$(curl --max-time 30 --connect-timeout 10 -sk -o /tmp/metrics_${ep}.txt -w "%{http_code}" \ How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
The target uses modern observability tooling (Go, .NET, Java, Node.js). These frameworks often expose /metrics, /health, and /status endpoints that are forgotten behind auth. Unlike application data leaks, metrics leaks reveal the ENTIRE operational profile: which AI models are used, how many users are active, database connection exhaustion, and third-party service dependencies.
Phase 1 — Discover Metrics Endpoints
TARGET="https://target.com"
# Common observability paths
for ep in metrics health status ready live readyz healthz \
actuator/health actuator/metrics actuator/prometheus \
Telescope telescope horizon debug; do
code=$(curl --max-time 30 --connect-timeout 10 -sk -o /tmp/metrics_${ep}.txt -w "%{http_code}" \
"${TARGET}/${ep}" 2>/dev/null)
if [ "$code" = "200" ]; then
size=$(wc -c < /tmp/metrics_${ep}.txt)
echo " /${ep}: HTTP 200 (${size} bytes)"
fi
done
Phase 2 — Analyze Prometheus Metrics
# Count unique metric families (each reveals a subsystem)
grep -c '^# HELP' /tmp/metrics_metrics.txt
# Extract AI/ML model usage
grep -i 'ai_\|model\|llm\|openai\|gemini\|copilot' /tmp/metrics_metrics.txt
# Extract database pool states
grep -i 'db_pool\|database\|connection' /tmp/metrics_metrics.txt
# Extract third-party dependencies
grep -i 'stripe\|openai\|sendgrid\|twilio\|email' /tmp/metrics_metrics.txt
# Extract request volumes (user activity)
grep -i 'http_request\|api_request\|grpc_request' /tmp/metrics_metrics.txt
# Extract circuit breaker states (service health)
grep -i 'circuit_breaker' /tmp/metrics_metrics.txt
Phase 3 — Analyze Health/Status Endpoints
# Spring Boot Actuator
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/actuator/health" | python3 -m json.tool
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/actuator/metrics" | python3 -m json.tool
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/actuator/env" | python3 -m json.tool # May leak env vars
# Custom health endpoints
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/health" | python3 -m json.tool
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/api/health" | python3 -m json.tool
# Laravel Telescope (if exposed)
curl --max-time 30 --connect-timeout 10 -sk "${TARGET}/telescope/requests" | head -c 500
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.
- 9d ago First seen · 139 lines · 29 tokens per session scan C 2bdb1e3999dc
hunt-metrics-exposure is a skill published in the GitHub repository uphiago/recon-skills (1,254 stars, last pushed 11d ago), licensed MIT. It adds 29 tokens to every session and 1,382 once invoked, about $0.0001 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.
detecting-s3-data-exfiltration-attempts
Detecting data exfiltration attempts from AWS S3 buckets by analyzing CloudTrail S3 data events, VPC Flow Logs, GuardDuty findings, Amazon Macie alerts, and S3 access patterns to identify unauthorized bulk downloads and cross-account data transfers.
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-aws-security-hub-compliance
Implementing AWS Security Hub to aggregate security findings across AWS accounts, enable compliance standards like CIS AWS Foundations and PCI DSS, configure automated remediation with EventBridge and Lambda, and create custom security insights for organizational risk management.
implementing-azure-defender-for-cloud
Implementing Microsoft Defender for Cloud to enable cloud security posture management, workload protection across VMs, containers, databases, and storage, configure security recommendations, and set up adaptive security controls with automated remediation.