Skills/npm/chat-recall

chat-recall@0.7.26

CAUTION

Publisher claims: "Shared team knowledge, leaked-secret alerts, ranked code findings and tracked tasks, across every AI coding tool you use" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher munhq · joined 0 days agoInstalls 3,345Last detonated 5 h ago

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-03 and scored it 62/100 (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; Hidden zero-width characters detected; Auto-update or dynamic fetch configuration. 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

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentdist/project-tasks.js:192 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Hidden zero-width characters detecteddist/scan-worker.js:8459 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.js:6 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/intent-drain.js:288 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Outbound HTTP to raw IP addressdist/hostile-server.js:97 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commanddist/keyring.js:73 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.js:4 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Outbound HTTP to raw IP addressdist/hostile-server.js:82 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.d.ts:21 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/intent-drain.js:285 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/http.js:10 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.js:47 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Hidden zero-width characters detecteddist/repair.d.ts:14 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.js:79 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commanddist/keyring.js:72 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detecteddist/repair.js:14 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Outbound HTTP to raw IP addressdist/hostile-server.js:68 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.js:90 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.d.ts:51 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
URL with embedded credentialsdist/scan-worker.js:5116 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/auto-update.d.ts:176 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddist/mcp-socket.d.ts:42 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL using raw IP addressdist/hostile-server.js:68 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressdist/hostile-server.js:97 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/sync-client.js:1209 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/self-restart.js:33 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commanddist/mcp-socket.d.ts:44 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actiondist/install-hooks.js:241 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL using raw IP addressdist/hostile-server.js:82 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commanddist/mcp-socket.js:138 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/sync-client.js:1212 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/scan-worker.js:5101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/sync-client.js:1456 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddist/mcp-socket.js:140 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddist/self-restart.d.ts:33 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/sync-client.js:1453 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/update-notice.js:4 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/sync-delegate.js:4 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionpackage.json:59 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/sync-client.js:2128 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Unpinned dependencydist/update-notice.js:63 · Unpinned dependencyFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim munhq: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim munhq