black-fortress@1.1.10
VERIFIED· install onlyPublisher claims: "Pre-installation agentic sandboxing protocol. 5-layer defense: semantic neutralization, hard quarantine, kernel ground-truth, trusted output rendering, and s..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
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 2026-11-15 and scored it 82/100 (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 deviationsStatic findings
"""Layer 1: Obfuscate all source code to kill semantic injection."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.… This is **Layer 1** and **Layer 3** at work. We aggressively strip comments to kill prompt-injections, and we analyze the Shannon Entropy of outputs to detect hidde…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…Docker commands are now built as **argument lists** (no shell interpretation). `subprocess.run(cmd)` with a list never invokes `/bin/sh`, so path metacharacters are treated as…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.echo '{"credsStore":"osxkeychain"}' > ~/.docker/config.jsonFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| `/bin/sh` / `/bin/bash` | ❌ | No reverse shell, no `os.system()` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.