Skills/ClawHub/shieldcortex

shieldcortex@5.20.2

VERIFIED· install only

Publisher claims: "Memory and defence for AI agents: semantic recall, knowledge graph and decay, plus a memory firewall that scans and enforces against prompt injection, credential leaks and poisoning." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jarvis-drakon · publishing for 31 daysInstalls 9,530Last detonated 32 min ago
$clawhub install shieldcortex
WatchReport an issue

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 changed since 5.20.0

vet-skills diff shieldcortex 5.20.0 5.20.2

In the sandbox, this version reached for nothing 5.20.0 did not. Compared from the two recorded runs, not from source.

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-18 and scored it 84/100 (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 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 type combined with upload actionSKILL.md:67 · File type combined with upload action — agent may exfiltrate local data files…ry or conversation content. `actionGuard.packageVetting.enabled false` in config.json always stops the watch's lookups, policy lock or not, because the watch reads config.json as written; it stops the tool-call lookups only on a host witho…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsSKILL.md:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- $CWD/.env (env-scanner checks for leaked secrets — reads, never writes)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:306 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- **Not uploaded by default:** local agent configs, MCP configs, raw rules files, shell configs, SSH keys, secrets, `.env` contents, or arbitrary project files.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:66 · npx invocation of non-well-known package — may execute untrusted code…d, but with no separate host allowlist; and the OpenClaw `cortex-memory` hook's npx package resolution (`npx mcporter`, and `npx -y shieldcortex` when no accessible `binar…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:43 · npx invocation of non-well-known package — may execute untrusted code… updates and X-Ray package lookups, and the OpenClaw `cortex-memory` hook's npx package resolution (`npx mcporter`, and `npx -y shieldcortex` when no accessible `binar…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsSKILL.md:297 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- **Environment** — .env files for leaked credentials (read-only check, never writes)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionSKILL.md:115 · File type combined with upload action — agent may exfiltrate local data files…alse` stops it, policy lock or not (the watch reads `enabled: false` from config.json as written). That is the watch only: under a verified or unverifiable policy lock or the strict fail-closed posture, `enabled: false` is dropped for the …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈9,383 tok
1 file · 2 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.

shieldcortex@5.20.2 safety verdict: Verified (install only) — KillerSkills