━━ policy pack
FailproofAI/policies
Policy packs for failproofai. Install with: failproofai pack add FailproofAI/policies
packs are published by their authors, not audited by failproof ai. read the source before you install.[ read more ↓ ]
━━ take part of it
with no flags you get the pack's own defaults and are shown the rest — what its author marked safe to switch on unattended, not everything it contains. these three skip that.
- one policy
- one category
- look first
this pack gets no special delivery path and no shorter spelling. it is installed by owner/repo, checksummed and pinned exactly like anybody else's — the npm package ships no policy pack at all. the only policy that is ON without one is the always-on self-protection guard, block-failproofai-commands, which cannot travel the pack lane because a pack may not declare alwaysOn.
━━ 38 policies · 9 categories
sanitize5
- sanitize-jwt
Stop Claude from reading JWTs in tool responses
- sanitize-api-keys
Stop Claude from reading API keys (OpenAI, Anthropic, GitHub, AWS, Stripe, Google) in tool responses
- sanitize-connection-strings
Stop Claude from reading database connection strings with embedded credentials in tool responses
- sanitize-private-key-content
Stop Claude from reading PEM private key content in tool responses
- sanitize-bearer-tokens
Stop Claude from reading Authorization Bearer tokens in tool responses
environment3
- protect-env-vars
Prevent commands that read environment variables
- block-env-files
Block reading/writing .env files
- block-read-outside-cwd
Block file reads outside the session working directory
dangerous commands4
- block-sudo
Block sudo commands
- block-curl-pipe-sh
Block piping downloads to shell
- block-rm-rf
Prevent catastrophic deletions
- block-secrets-write
Block writing secret key files
infra commands7
- block-kubectl
Block kubectl commands (Kubernetes cluster mutations)
- block-terraform
Block terraform and tofu (OpenTofu) commands
- block-aws-cli
Block aws CLI commands
- block-gcloud
Block gcloud (Google Cloud) CLI commands
- block-az-cli
Block az (Azure) CLI commands
- block-helm
Block helm commands
- block-gh-pipeline
Block gh CLI pipeline-trigger subcommands (workflow run, run rerun/cancel, pr merge, release create/delete, cache delete, secret set/delete)
git6
- block-push-master
Block pushing to main/master
- block-force-push
Prevent force-pushing to any branch
- block-work-on-main
Block git commits and merges on main/master branch
- warn-git-amend
Warns before amending git commits, which rewrites history
- warn-git-stash-drop
Warns before permanently deleting stashed changes
- warn-all-files-staged
Warns before staging all working tree files with git add -A / . / --all
database2
- warn-destructive-sql
Warn before executing destructive SQL (DROP/TRUNCATE/DELETE without WHERE) via database clients
- warn-schema-alteration
Warns before SQL schema changes (ALTER TABLE with column or rename operations)
packages & system5
- warn-package-publish
Warn before publishing packages to public registries (npm, PyPI, crates.io, RubyGems, etc.)
- warn-global-package-install
Warns before installing packages globally (npm -g, cargo install, etc.)
- prefer-package-manager
Blocks non-preferred package managers and tells Claude to use an allowed one (e.g., uv instead of pip)
- warn-large-file-write
Warn before writing files larger than 1MB (configurable via thresholdKb param)
- warn-background-process
Warns before starting detached or background processes
ai behavior1
- warn-repeated-tool-calls
Warn when the same tool is called 3+ times with identical parameters
workflow5
- require-commit-before-stop
Require all changes to be committed before Claude stops
- require-push-before-stop
Require all commits to be pushed to remote before Claude stops
- require-pr-before-stop
Require a pull request to exist for the current branch before Claude stops
- require-no-conflicts-before-stop
Require the current branch to merge cleanly with the base branch before Claude stops
- require-ci-green-before-stop
Require CI checks to pass on the current HEAD commit before Claude stops (ignores stale runs on prior commits)
the hub reads this pack's manifest and verifies it against the release's own SHA256SUMS. it never downloads or runs failproofai-pack.mjs — what you see here is what policies add would install.
━━ review before you install
packs are published by their authors. failproof ai does not review, audit, or certify them, and listing here is not an endorsement. the hub checksums every pack against the SHA256SUMS in its own release — that proves the file is the one that release published, and nothing else. it is not a signature: whoever controls the release controls both files, so it says nothing about who wrote the code, and nothing about whether the code is safe.
read the source before you install. a policy runs inside your agent's hook path on every call it matches, and sees the tool input your agent is about to act on. treat a third-party pack exactly as you would any other dependency you are about to give that access to.
this pack's source: FailproofAI/policies ↗ · preview what it contains without downloading or running any of it with failproofai policies show FailproofAI/policies.