Skills/Glama/kronicle-lite

kronicle-lite@0.11.2

CAUTION· install only

Publisher claims: "A local-first, SQLite-backed document store that lets agents keep notes on a verifiable hash chain and receive signed receipts on recall, so it can flag when previously read information has been superseded or retired. An orient call reports what changed since the agent's last cursor, including a drift banner and retraction list, so stale beliefs surface instead of silently misleading." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher isokron-ai · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

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

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso isokron.ai, sectigo.com, digicert.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

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 2026-11-11 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Credential pass-through configuration; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandsrc/doctor.ts:120 · File permission modification command — agent changes file ownership/permissionsproblems.push(`data dir is ${octal(dm)} (expected 0700: chmod 700 ${dataDir})`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Destructive file system command detectedsrc/cli.ts:272 · Destructive file system command detectedmust be format /3, anchors must close the freeze, the last runFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Credential pass-through configurationsrc/secrets/guard.ts:75 · Credential pass-through configuration — agent relays sensitive credentials* token(s) key the value must also pass tokenValueOk (0.11.2).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
npx invocation of non-well-known packagesrc/audit/package.ts:725 · npx invocation of non-well-known package — may execute untrusted code`npx -y kronicle-lite@${VERSION} verify-audit . --key-fingerprint <the auditor key fingerprint from your statement of work>${v.genesisArg}${v.profile === 'legacy' ? ' --profile legacy' : ''}`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/audit/package.ts:484 · npx invocation of non-well-known package — may execute untrusted code… `Claims ${claims.claims.join(', ')}`, '', `Verify: npx -y kronicle-lite@${VERSION} verify-audit <this directory> --key-fingerprint <audit…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedsrc/audit/schemas.ts:18 · Destructive file system command detected/** Audit milestones (0.10.0): a bundle holding any of these is written as format /2 (0.9.0 readers refuse it by format). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/shim/script.ts:284 · Privileged sudo command — agent may execute with elevated privileges/** The default store when not pinned, absolute (a hook may run under sudo or `env -i`, with another HOME). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedsrc/stdio.ts:61 · Hidden zero-width characters detected — may conceal contentconst BOM = '';Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/server.ts:283 · MCP server using network transport (SSE/HTTP) — data sent over network/** Factory form for the SDK serving entries: one fresh McpServer per connection (stdio) or request (HTTP). */Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Instructs the agent to modify its persistent memory or instruction filesexamples/README.md:17 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileand add the line from `examples/.claude/CLAUDE.md` to your `CLAUDE.md`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandsrc/doctor.ts:137 · File permission modification command — agent changes file ownership/permissionsproblems.push(`${f.name} is ${octal(m)}, readable by others (expected 0600: chmod 600 ${join(dataDir, f.name)})`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Destructive file system command detectedsrc/audit/schemas.ts:20 · Destructive file system command detected/** Audit-profile kinds (0.11.0): a bundle holding any of these, or a planned freeze, is written as format /3. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/audit/schemas.ts:16 · Destructive file system command detected/** The 0.9.0 kinds: a bundle that holds only these is written as format /1, which 0.9.0 readers verify. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/anchor/client.ts:246 · File type combined with upload action — agent may exfiltrate local data filesthrow this.refusal(r.status, r.json, r.isJson, 'POST /v1/anchor');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandsrc/shim/cli.ts:326 · Privileged sudo command — agent may execute with elevated privileges… hook: pushes git starts itself (aliases, hooks, rebase -x, submodule foreach), sudo and absolute paths are not checked (shim install --git-hook)`); } if…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,503 tok
1 file · 80 in bundle

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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim isokron-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim isokron-aiPropose a patch to the maintainer