smart-memory@3.1.0
CAUTION· install onlyPublisher claims: "Persistent local transcript-first memory for OpenClaw via a Node adapter and FastAPI engine." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 73 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 3 scenarios · 0 deviationsStatic findings
from .core_memory_manager import CoreMemoryManagerFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Migration helpers from legacy JSON stores into the v3 SQLite backend."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.auto_update_from_context(user_message, assistant_message)Fix: Pin versions and sources; vendor anything fetched at install time."""Entity alias resolution utilities."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Prompt Composer orchestration."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.from hot_memory_manager import get_hot_memory_for_compose, auto_update_from_contextFix: Pin versions and sources; vendor anything fetched at install time.def auto_update_from_context(user_message: str, assistant_message: str):Fix: Pin versions and sources; vendor anything fetched at install time."""Entity package exports."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.from .eval_runner import EvalRunnerFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# Usage: curl -sL https://raw.githubusercontent.com/BluePointDigital/smart-memory/master/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Memory type classifier for ingestion."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Deterministic entity normalization helpers."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Usage: curl -sL https://raw.githubusercontent.com/BluePointDigital/smart-memory/master/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.{Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."""Transcript append helpers for Smart Memory v3.1."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Candidate memory re-ranking for retrieval context selection."""Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."use strict";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Usage: curl -sL https://raw.githubusercontent.com/BluePointDigital/smart-memory/master/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Canonical data schemas for Smart Memory v3.1."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Storage helpers for Smart Memory."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Transcript-first models for Smart Memory v3.1."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Transcript subsystem exports."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.subprocess.Popen(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Legacy JSON import/export store for long-term memory objects."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""SQLite-backed transcript storage for Smart Memory v3.1."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."use strict";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Action selection policies for memory revision."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Conflict detection for revision-aware memory writes."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."use strict";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Prompt rendering with strict prompt-level token enforcement."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Token budget allocation for prompt composition."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.from .conflict_detector import ConflictDetector, ConflictResultFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim bluepointdigital: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.