lineage-package-security-guardrailslisted
Install: claude install-skill agentic-lineage/lineage
# Lineage Package Security Guardrails
Lineage packages are portable local environments. A receiver should be able to inspect what a package will do before it changes their workspace.
## Threat Model
Assume every package is untrusted until validated. A malicious or careless package may try to:
- include secrets or private local state;
- reference files outside the package;
- write outside the intended workspace;
- smuggle symlinks or path traversal entries;
- hide risky setup actions behind normal activation;
- make provider-specific assumptions look like core behavior.
## Safety Rules
- Import and inspect must not execute setup actions.
- Setup and materialization must be explicit, reviewable, permission-gated, and idempotent.
- Never package API keys, auth tokens, `.env` values, credential stores, provider login state, shell history, or machine-local caches.
- Secret checks may report file paths and reasons, but not matched values.
- Prefer templates, schemas, sample CSVs, and placeholder config when private source data should not travel.
- Validate every package-controlled path before reading or writing. Absolute paths and `..` traversal are unsafe unless a specific user-provided destination explicitly allows them.
- Reject or deliberately handle symlinks. Do not silently follow package symlinks into the receiver's machine.
- Keep capability declarations honest and human-readable. Do not imply enforcement exists until code actually enforces it.
## Review Questions
-