Skills/ClawHub/agentshield

agentshield@2.0.2

CAUTION· install only

Publisher claims: "AI Agent Detection & Response — real-time security monitoring with Sigma rules and LLM-powered triage" Observed in sandbox: sends data to release-assets.githubusercontent.com.

Registry ClawHubPublisher markbriers · publishing for 260 daysInstalls 1,381Last detonated 1 h ago

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 · 1 of 1 bundled script run with no arguments, 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

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 2026-11-18 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Access to sensitive file paths. Summary: sends data to release-assets.githubusercontent.com.

Behavior trace

Honeypot run · 3 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
1.0snetworkCONNECT tcp://api.github.com:443
1.0snetworkCONNECT tcp://github.com:443
1.0snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
1.0sprocessexec /usr/bin/uname
1.0sprocessexec /usr/bin/tr
1.0sprocessexec /usr/bin/grep
1.0sprocessexec /usr/bin/curl
1.0sprocessexec /usr/bin/cut
1.0sprocessexec /usr/bin/mktemp
1.0sprocessexec /usr/bin/rm
1.0sprocessexited 1: curl: (56) CONNECT tunnel failed, response 403
1.1sprocessbundled script run in the sandbox with no arguments
1.1sprocess1 of 1 bundled script run with no arguments
1.1sprocessscript backend runs setup only
1.1sprocessscript backend runs setup only
1.8sprocesssecond launch, clock +45 days, CI unset
2.5snetworkCONNECT tcp://api.github.com:443
2.5snetworkCONNECT tcp://github.com:443
2.5snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
2.5sprocessexec /usr/bin/tr
2.5sprocessexec /usr/bin/uname
2.5sprocessexec /usr/bin/curl
2.5sprocessexec /usr/bin/grep
2.5sprocessexec /usr/bin/cut
2.5sprocessexec /usr/bin/mktemp
2.5sprocessexec /usr/bin/rm
2.5sprocessexited 1: curl: (56) CONNECT tunnel failed, response 403

Static findings

HIGH
Access to sensitive file pathsSKILL.md:235 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- '/etc/shadow'Fix: 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 configurationSKILL.md:243 · Auto-update or dynamic fetch configuration — agent may load new code at runtime- Hot reload is enabled by default (`rules.hot_reload: true`)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsinstall.sh:132 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesselection: {tool: file_operation, path|contains: ['/etc/passwd', '/etc/shadow', '.ssh/']}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commanduninstall.sh:50 · Process kill command — agent can terminate processesif kill -0 "$e2e_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanduninstall.sh:52 · Process kill command — agent can terminate processeskill "$e2e_pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationSKILL.md:82 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationinstall.sh:153 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsSKILL.md:234 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- '/etc/passwd'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandinstall.sh:90 · File permission modification command — agent changes file ownership/permissionschmod +x "$INSTALL_DIR/bin/agentshield"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,355 tok
1 file · 6 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

25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim markbriers: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim markbriersPropose a patch to the maintainer