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 catpilotai/catpilot-ai-guardrails --skill catpilot-security-coregit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/catpilot-security-core)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/catpilot-security-core"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/catpilot-security-core/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/catpilotai/catpilot-ai-guardrails/catpilot-security-core"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/catpilot-security-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00128 | $0.04920 |
| Opus 5.5 | $0.00051 | $0.01968 |
| Sonnet 5.5 | $0.00026 | $0.00984 |
| Haiku 4.5 | $0.00013 | $0.00492 |
Grade C, and why
catpilot-security-core 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 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Piping `~/.ssh`, `~/.aws`, or an `env` dump into a network request, or untrusted content into `sudo bash`/`sudo sh`. 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.
- Replace `curl | bash`-style pipe-to-shell installs with download, hash-verify, inspect, then run; prefer the project's package-manager distribution. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf`/`find ... -delete` against an unset or unguarded variable, or any path outside the project directory. 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.
**Applies when:** Every code generation, file write, file edit, and diff review, and any shell command with inline credentials, environment-variable assignments, or `curl -H` headers. How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catpilot Security Core
Catpilot's universal security baseline for AI coding agents, intended to apply on every file write, diff review, and shell command the agent is about to run, regardless of language or framework, whenever the host has loaded this skill. It is advice the agent reads: installing this bundle is not activation, and an instruction the agent has read is not an enforced control. The repository's protection contract explains the difference between advice, coaching, and enforcement.
This file is deliberately short. Each component below names its reference
file, states when it applies, and lists the rules that always hold. Do not
answer from this file alone: before acting in a component's area (a cloud
command that changes infrastructure, a database migration or data change, a
Dockerfile, a dependency change, anything that handles a secret or real
personal data, or code in the language-baseline patterns), read the named
reference file with your file-reading tool and follow it. The examples, the
remediation steps, and the detection patterns live there, and so do the
facts that decide whether a command is safe. Component IDs match the catpilot-components entry in the frontmatter and
the bundle.components list in catpilot.json next to this file, so a
finding can be mapped back to a specific source skill (and to its severity,
version, and control mappings).
This bundle is generated deterministically from
src/skills/core/<id>/SKILL.md by tools/bundle.py in the
catpilotai/catpilot-ai-guardrails repository. Edits to this file or to the
reference files are overwritten on the next bundle. To change behavior, edit
the corresponding source skill and rebuild.
cloud-cli-safety
Before acting in this area, read references/cloud-cli-safety.md in this skill's directory; the rules below are the minimum, not the whole component.
Applies when: Before invoking a mutating az, aws, gcloud/gsutil, kubectl, helm, or terraform command, or a custom deploy wrapper (./deploy.sh, make deploy), especially against production-heuristic targets.
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.
- catpilot.json 3.8 KB
- references/cloud-cli-safety.md 18 KB
- references/database-safety.md 15 KB
- references/docker-safety.md 16 KB
- references/language-baseline.md 18 KB
- references/local-cli-safety.md 15 KB
- references/pii-and-test-data.md 17 KB
- references/secret-blocking.md 13 KB
- references/secrets-management.md 17 KB
- references/supply-chain.md 18 KB
- scripts/cloud-cli-safety/env_patch.py 2.5 KB runs code
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 Changed d68540526680
- 1mo ago Changed · -3,392 lines scan E → C 13709349067f
- 1mo ago Changed · +16 lines · +18 tokens per session 84e0ca745805
- 2mo ago First seen · 3,648 lines · 110 tokens per session scan E 90c01b5ab0d6
catpilot-security-core is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 8d ago), licensed MIT. It adds 128 tokens to every session and 4,920 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
catpilot-security-core compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| catpilot-security-corecatpilotai/catpilot-ai-guardrails | Skill | 2 | 8d ago | MIT | C | 128 | Claude Code |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| baoyu-article-illustratorNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| flash-attentionNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| subagent-driven-developmentNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 17 | Claude Code, Codex |
| mcporterNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 16 | Claude Code, Codex |
| mem0-vercel-ai-sdkmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 146 | Claude Code, Codex |