Sovereign Intelligence System - Equilibrium-native reasoning for OpenClaw

Adds equilibrium-constrained reasoning to OpenClaw, ensuring all operations maintain balance for coherent, self-validating, and consistent AI responses.

This package mostly implements what the SKILL.md promises (equilibrium symbols, validator, VM, and a vault). Before installing: 1) Inspect and remove or understand the hardcoded path insertion (symbols/taxonomy.py: sys.path.insert(0, '/home/claude/sis')) — that is the primary red flag because it changes import behavior and can cause the skill to load unexpected code from the host. 2) Decide whether you trust file persistence: FileVault will create ./nexuseternal_vault in the agent working directory; ensure that location and contents are acceptable. 3) If you enable PostgresVault or replication, plan how credentials and network endpoints will be provided (they are not declared in the manifest) and run the code in a sandbox first. 4) Note license/header inconsistencies (PROPRIETARY wording vs MIT license) and minor metadata oddities (no registry description); these suggest sloppy packaging rather than explicit malice, but review source before use. If you want to proceed safely: run the skill in an isolated environment, review/strip the sys.path insert, and avoid enabling external backends until you supply vetted connection settings.

Type: OpenClaw Skill Name: sis-skill Version: 1.0.0 The skill bundle is classified as suspicious due to the presence of risky capabilities without clear malicious intent. Specifically, the `symbols/taxonomy.py` file contains a hardcoded `sys.path.insert(0, '/home/claude/sis')` which is a direct manipulation of the Python import path and could be exploited for arbitrary code loading if the specified path is compromised. Additionally, the `persistence/vault.py` module implements a `FileVault` that performs local file system I/O (e.g., `os.makedirs`, `open`, `json.dump`) and declares an unimplemented `PostgresVault` that imports `psycopg2`, indicating an intent for network/database interaction. While these capabilities are plausibly related to the skill's stated purpose of 'persistence' and 'computational substrate', the `sys.path.insert` in particular represents a significant security risk.