kb-agentic-skill@1.39.0
CAUTION· install onlyPublisher claims: "Knowledge-Base & Document-First protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, signal distillation and optional devPNT integration." 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 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
What changed since 1.37.0
vet-skills diff kb-agentic-skill 1.37.0 1.39.0This version reaches for something 1.37.0 did not: 1 new install script (node scripts/postinstall.js). Compared from the two recorded runs, not from source.
- New install scripts
- node scripts/postinstall.js
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-17 and scored it 71/100 (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; HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 2 s · 3 scenariosStatic findings
# router: a router throw must not kill this line. It measures NOTESFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.INVISIBLE = re.compile("[--]")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.generated by scripts/whats_new.js from distributions/kb-agentic-skill/CHANGELOG.md: edit the CHANGELOG, then run node scripts/whats_new.js --writeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.r = subprocess.run(["git", "rev-parse", "--is-inside-work-tree"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["git", "diff", "--name-only", ref, "--", rel_path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["git", "status", "--porcelain", "--", rel],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["git", "rev-parse", "--short=12", "HEAD"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.[gate] The promises that outrank everything: what the user is guaranteed, what the architecture must always be true of. State each as ONE decision question withFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Interview question 1: ONE concrete case that today does not get the expected result, with its example — never a missing feature. Cite the answer (REQUEST_[topicFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.r2 = subprocess.run(["git", "ls-files", "--others", "--exclude-standard", "--", rel_path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.console.log('👉 npx kb-agentic-init');Fix: Pin versions and sources; vendor anything fetched at install time.r = subprocess.run(["git", "check-ignore", "-q", str(out)], cwd=str(project),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.s = s.replace(/[--]/g, "");Fix: 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
No advisories in OSV for @antoneeo/kb-agentic-skill@1.39.0 as of 6 min ago. This is the package itself, not its dependencies.
What would make this Verified
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim antoneeo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.