agent-context-system@1.3.2
CAUTION· static onlyPublisher claims: "A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at session start, update the scratchpad at session end, and promote stable patterns over time. Works across Claude Code, Cursor, Copilot, Windsurf. Subagent-ready. No plugins, no infrastructure, no background processes." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 52/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
CRITICAL: This section is the most important part of this file. Vercel's evals showed passive context (always in prompt) achieves 100% pass rate vs 53% when ageFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- Run `agent-context promote --autopromote` to automatically append flagged patterns to AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.1. **Edit `AGENTS.md`** — Fill in your project name, stack, commands. Replace placeholders with real patterns from your codebase.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chmod +x scripts/publish-template.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# Wrapper for backwards compatibility with npx skills install.Fix: Pin versions and sources; vendor anything fetched at install time.1. **Edit `AGENTS.md`.** Fill in your project name, stack, commands. Replace the placeholder patterns and gotchas with real ones from your codebase. This is the highest-leverage edit you'll make.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx skills add AndreaGriffiths11/agent-context-systemFix: Pin versions and sources; vendor anything fetched at install time.sensitive_files=$(find . -maxdepth 2 \( -name ".env*" -o -name "*.pem" -o -name "*.key" -o -name "*.secret" -o -name "id_rsa*" \) 2>/dev/null || true)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.rm -rf /tmp/acsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.4. **Promote**: Run `agent-context promote` to review, or `--autopromote` to auto-append to `AGENTS.md`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chmod +x scripts/init-agent-context.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- [GitHub: How to Write a Great AGENTS.md](https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# If you installed as a skill (npx skills add):Fix: Pin versions and sources; vendor anything fetched at install time.Then edit `AGENTS.md` with your project specifics: name, stack, commands, actual patterns and gotchas from your codebase. This is the highest-leverage edit you'll make.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ser's project directory, gitignored. The trust model is the same as `.bashrc`, `.env`, or IDE config files — if an attacker can write to your local project files, a…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><strong>The Research (Why this works)</strong></summary> ### Agents have an instruction budget (~150-200 instructions) HumanLayer found frontier LLMs rFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ser's project directory, gitignored. The trust model is the same as `.bashrc`, `.env`, or IDE config files — if an attacker can write to your local project files, a…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.
What would make this Verified
28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim andreagriffiths11: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.