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 getsentry/warden-skills --skill wrdn-code-executiongit clone --depth 1 https://github.com/getsentry/warden-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/getsentry/warden-skills/wrdn-code-execution)<a href="https://agentmods.dev/skills/getsentry/warden-skills/wrdn-code-execution"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-code-execution/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/getsentry/warden-skills/wrdn-code-execution"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-code-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 Tool Misuse · line 21 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 69 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 69 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 69 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 157 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high YARA Match · line 227 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
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 | $0.00102 | $0.04003 |
| Opus 5.5 | $0.00041 | $0.01601 |
| Sonnet 5.5 | $0.00020 | $0.00801 |
| Haiku 4.5 | $0.00010 | $0.00400 |
Grade A, and why
wrdn-code-execution scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Identify the sink.** Is it actually dangerous in the form used? `subprocess.run(["ls", user_arg])` is safe. `subprocess.run(f"ls {user_arg}", shell=True)` is not. How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior application security engineer. You hunt bugs where untrusted input reaches a sink that executes code on the server. These are high-impact bugs: they produce the attacker a shell, a new privilege, or the ability to pivot to credential theft.
The abstract shape is constant across languages:
untrusted source ──▶ (missing validation / unsafe API) ──▶ code-execution sink
This skill covers cases where the primary impact is arbitrary code or commands executing. Some sinks straddle multiple impact classes: XXE can read files or reach RCE gadgets, and command injection can exfiltrate files. Report here only when the code-execution path is concrete.
Trace. Do Not Skim.
The sink tells you what could happen. The source tells you whether it will. Trace before reporting.
- Identify the sink. Is it actually dangerous in the form used?
subprocess.run(["ls", user_arg])is safe.subprocess.run(f"ls {user_arg}", shell=True)is not. - Identify the source. Values from
request.body,request.query,request.headers, parsed webhook payloads, third-party API responses, file uploads, user-controlled config are untrusted. Hardcoded constants and server-side-derived values are not. - Trace the path. Read the function, the caller, and whatever validation sits between. A Pydantic schema with strict types may sanitize the sink argument; a Zod
z.string()with no regex may not. - Check the library version.
yaml.loadwithoutSafeLoaderon PyYAML < 5.1 is unsafe by default.jsonwebtoken.verifybefore 9.0 allows algorithm confusion.vm2in any version is abandoned and RCE-prone. - Use the shell.
git log -p <file>shows whether a validation step was recently removed.rg -n '<sink>'enumerates siblings so you can compare the analysis. - Detect the framework. Load the matching reference for framework-specific idioms and defaults.
If the trace cannot be completed with the files at hand, drop the finding or report with lower confidence.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/command-injection.md 8.0 KB
- references/deserialization.md 7.8 KB
- references/django.md 3.0 KB
- references/eval.md 6.7 KB
- references/express.md 4.3 KB
- references/fastapi.md 3.1 KB
- references/flask.md 2.8 KB
- references/nextjs.md 3.9 KB
- references/prototype-pollution.md 7.0 KB
- references/sentry.md 5.2 KB
- references/ssti.md 6.7 KB
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.
- 1mo ago First seen · 320 lines · 102 tokens per session scan A a775fa05db07
wrdn-code-execution is a skill published in the GitHub repository getsentry/warden-skills (57 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 4,003 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
django-perf-review
Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.
gha-security-review
GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks.…
presentation-creator
Create data-driven presentation slides using React, Vite, and Recharts with Sentry branding. Use when asked to "create a presentation", "build slides", "make a deck", "create a data presentation", "build a Sentry presentation". Scaffolds a complete slide-based app with charts, animations, and single-file HTML output.
triage-frontend-issues
Triage new issues in the Sentry javascript project by archiving non-actionable noise. Use when asked to "triage issues", "triage the javascript project", "archive non-actionable issues", "triage new frontend issues", or "clean up the sentry/javascript queue". Operates only on the sentry/javascript project, only…
pr-screenshots
Capture screenshots of the Sentry UI in a web browser, lay them out in a pull request description as before/after tables, and upload them with gh --attach.
iterate-pr
Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.