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 adriannoes/awesome-agentic-ai --skill supply-chain-attack-recongit clone --depth 1 https://github.com/adriannoes/awesome-agentic-aiWrote 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/adriannoes/awesome-agentic-ai/supply-chain-attack-recon)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/supply-chain-attack-recon"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/supply-chain-attack-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/adriannoes/awesome-agentic-ai/supply-chain-attack-recon"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/supply-chain-attack-recon.svg" alt="Reviewed on agentmods" width="80" 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 Privilege Escalation · line 141 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.
- high Privilege Escalation · line 274 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.
- high Privilege Escalation · line 329 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.
- high Privilege Escalation · line 356 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.
- high YARA Match · line 383 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 MCP Rug Pull · line 242 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Data Exfiltration · line 266 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 266 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 | $0.00141 | $0.04604 |
| Opus 5 | $0.00071 | $0.02302 |
| Sonnet 5 | $0.00028 | $0.00921 |
| Haiku 4.5 | $0.00014 | $0.00460 |
Grade B, and why
supply-chain-attack-recon scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s "https://api.osv.dev/v1/query" -d '{"package": {"name": "lodash", "ecosystem": "npm"}, "version": "4.17.10"}' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **`hunt-cloud-misconfig`** — Container registries (Docker Hub, GHCR, ECR public) frequently expose private images by accident. Chain primitive: SBOM mining reveals `internal-tools-v2:latest` referenced → check Docker H Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI "https://github.com/$guess" | grep -E "HTTP|status" | head -1 How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger when:
- Target has a public GitHub organization (find via OSINT)
- JS bundles reference internal-looking package names (
@target-internal/...,target-utils,target-shared) - Build logs, SBOMs, or
package-lock.jsonfiles are publicly accessible - Target uses CI/CD that's partially public (GitHub Actions, GitLab CI, Bitrise)
- Docker images on Docker Hub/GHCR/Quay belong to target org
- Findings include
npmrc/pip.conf/gradle.propertieswith internal registry URLs .github/workflows/*.ymlfiles reference internal tooling
Do NOT use for:
- Internal-network artifact registries (out of scope per external boundary)
- Actually publishing typosquats / dep-confusion packages without explicit OK
- Compromising upstream open-source projects (massive blast radius — illegal in most jurisdictions without authorization)
The supply-chain attack surface map
Target Org
├── Public GitHub Org → workflow files → secrets exfil opportunities
├── Internal package names in JS/Android bundles → dependency confusion
├── Docker images on public registries → secrets in layers, RCE on pull
├── SBOM / artifact metadata → exact dep versions for known-vuln chaining
├── npmrc / pip.conf in repos → internal registry URL disclosure
├── External package dependencies → typosquat name candidates
└── Build/release pipelines → injection if pull_request_target etc.
Step 1 — GitHub org discovery
TARGET="<brand>" # set to target brand name
# Direct guesses
for guess in $TARGET "${TARGET}-tech" "${TARGET}corp" "${TARGET}-io" "${TARGET}-eng"; do
curl -sI "https://github.com/$guess" | grep -E "HTTP|status" | head -1
done
# Via WHOIS / email-domain → GitHub search
gh search users --owner-affiliations=organization --query "$TARGET" --limit 10
# Via employees → reverse from social media + GitHub profile
# Many employees list their employer org on their GitHub profile
Step 2 — Enumerate public repos for sensitive artifacts
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 · 396 lines · 141 tokens per session scan B 2b84602d3057
supply-chain-attack-recon is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 141 tokens to every session and 4,604 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, harvests environment variables, 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
deployment
Use when taking an app from source to live: choosing the deploy target from requirements (Hetzner+Coolify vs Vercel vs a third), then wiring container → CI → registry → host with build secrets, healthchecks and rollback. NOT one platform's mechanics (that is coolify, vercel, railway, render), NOT the Dockerfile alone…
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.