brainx@0.3.5
VERIFIED· install onlyPublisher claims: "Vector memory engine with PostgreSQL + pgvector + OpenAI embeddings. Stores, searches, and injects contextual memories into LLM prompts. Includes auto-inject..." 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
- 8 of 10 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
./scripts/advisory-check.sh exec '{"command":"rm -rf /tmp/old"}' coderFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// Load env from .env file if presentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose../brainx-v5 advisory --tool exec --args '{"command":"rm -rf /tmp/old"}' --agent coder --jsonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# In agent SKILL.md or AGENTS.md, add:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.// Write a minimal fallback to MEMORY.md so the agent knows BrainX had issuesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.// 1. Update MEMORY.md (primary injection path)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.const path = process.env.BRAINX_ENV || require('path').join(__dirname, '..', '.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.dotenv.config({ path: path.join(BRAINX_DIR, ".env"), quiet: true });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| File read/write | `hook/handler.js` | Writes `BRAINX_CONTEXT.md` and updates `MEMORY.md` in the agent's workspace during bootstrap injection. |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Add to `AGENTS.md` in each workspace:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.const path = process.env.BRAINX_ENV || require('path').join(__dirname, '..', '.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- OpenClaw configuration (hooks, .env)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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.