slim-project-memory@1.0.3
VERIFIED· install onlyPublisher claims: "Use when a project's project memory file is over ~300 lines, when starting a new project from scratch, or when the user mentions context bloat, lost env URLs..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-22 and scored it 82/100 (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 · 0 s · 1 scenarios · 0 deviationsStatic findings
List env var NAMES here (not values), e.g.: | Anthropic | ANTHROPIC_API_KEY | Set in Railway dashboard | | Stripe | STRIPE_SECRET_KEY | Test mode only | Never pFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- "As you build the project, add new facts to the relevant `docs/` file, not directly to CLAUDE.md."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- "Open CLAUDE.local.md and add the env var name references — secrets go in Railway dashboard / .env files, not inline in this file."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…stead of inline values. Secrets go in environment variables (Railway dashboard, .env files, etc.) — not in project files. `CLAUDE.local.md` and `.env` must be gitig…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.6. Write each topical docs file using content extracted from CLAUDE.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.7. Write `docs/STATE-SNAPSHOT.md` with dated entity counts pulled from CLAUDE.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### A3. Write CLAUDE.md from the templateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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.