What is secret-blocking?

A security check that detects hardcoded passwords, API keys, tokens, private keys, and database connection strings before they reach files, commits, or logs.

It helps review generated code and diffs, inspect file edits and shell commands, recognise common provider-specific secret formats, and require environment variables instead of literal credentials.

It helps prevent credentials from being exposed in source code or git history, where removing them later may not protect them.

secret-blocking — Skill for Claude Code by catpilotai

Install

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.

Any agent

npx skills add catpilotai/catpilot-ai-guardrails --skill secret-blocking

Clone the repo

git clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrails

Made for: Claude Code.

Or install catpilot-guardrails, the plugin that ships this one along with the rest of its 25 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/secret-blocking/github.svg)](https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/secret-blocking)

Your own site

<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/secret-blocking"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/secret-blocking/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/secret-blocking"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/secret-blocking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,247 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00101	$0.04247
Opus 5.5	$0.00040	$0.01699
Sonnet 5.5	$0.00020	$0.00849
Haiku 4.5	$0.00010	$0.00425

Measured 1mo ago against content hash 8efc92e9431e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

secret-blocking 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.

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.

src/skills/core/secret-blocking/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baseline

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.

Always:

Scan every file write, edit, and diff for secret patterns before it lands, including shell commands with inline credentials or env assignments.
Stop and do not write the file when a detection pattern matches; name the provider to the user and propose an environment-variable or secret-manager remediation.
Treat a match for Stripe (sk_live_/sk_test_/rk_live_; publishable pk_ keys are not secrets), AWS (AKIA/ASIA/aws_secret_access_key), GitHub (ghp_/gho_/ghs_), GitLab (glpat-), Anthropic (sk-ant-), OpenAI (sk-), Slack (xox[abprs]-), Google (AIza/ya29.), a private-key block (-----BEGIN ... PRIVATE KEY-----), or a credentialed DB URI as a stop condition.
Use environment variables or a secret manager instead of a literal value.
Generate .env.example with placeholder values and confirm .env is in .gitignore.
Use clearly fake placeholders (your-api-key-here, REPLACE_ME) in example code, never realistic-looking strings.

Never:

Write a literal secret into source code, config files, comments, test fixtures, or documentation.
Echo a secret in a shell command the agent intends to run (e.g. curl -H "Authorization: Bearer sk-ant-...").
Paste a secret into a commit message, PR description, or issue body.
Write .env files containing real secrets.
Include a secret in a log statement, even at DEBUG level.

Open the full component before acting: it has the examples, the remediation steps, and the detection patterns.

When to apply

Apply on every code generation, file write, file edit, and diff review. Apply also on shell commands the agent is about to execute that include inline credentials, environment variable assignments, or curl -H headers.

This skill is one of the always-on critical skills. It is cheap to evaluate (regex over the diff or the proposed write), and the cost of a false negative is a leaked credential that ends up in git history forever.

Read the full file on GitHub · 332 lines

Changes

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 8efc92e9431e
1mo ago Changed · +21 lines b0975774e13e
2mo ago First seen · 311 lines · 101 tokens per session scan A 322b143b4621

Subscribe to this mod's changes

secret-blocking is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 8d ago), licensed MIT. It adds 101 tokens to every session and 4,247 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI Safety Claude Code Security agent-harness agent-skills ai-agents chatgpt

secret-blocking next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
secret-blockingcatpilotai/catpilot-ai-guardrails	Skill	2	8d ago	MIT	A	101	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

secret-blocking