Skills/ClawHub/skill-firewall

skill-firewall@1.0.5

BLOCKED· static only

Publisher claims: "Security scanner for AI agent skills (SKILL.md packs). Use before installing any skill from ClawHub, GitHub or external sources, when auditing a skill directory for malicious patterns (prompt injection, credential theft, exfiltration, destructive commands, obfuscated payloads, persistence), or when asked "is this skill safe?". Produces a SAFE/CAUTION/SUSPICIOUS/MALICIOUS verdict with evidence and CI-friendly exit codes. Strict by default; context-based severity reductions require an explicit opt-in." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher thiennhant95 · publishing for 1 daysInstalls 45Last detonated 26 min ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-15 and scored it 48/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionscripts/skill_firewall.py:161 · File type combined with upload action — agent may exfiltrate local data files…_rsa|\.env\b|credentials[\s_-]?file|\.netrc|MEMORY\.md|USER\.md|SOUL\.md|paired\.json)[^\n]{0,120}(-d |--data|--data-binary|-F |--form|-T |--upload-file|@/|@~|upload|exfiltrat|webhook)", # path-like secret + send mechanics (generic…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 pathsscripts/skill_firewall.py:133 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"(\bread\b|\bopen\b|\bfetch\b|\bcat\b)[^\n]{0,60}\.env(?!\.(example|sample|dist|template))",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 pathsscripts/skill_firewall.py:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…mp\b|\bprint\b|\bgrab\b|\bharvest\b|\bcollect\b|\bsteal\b|\bleak\b)[^\n]{0,80}(\.env(?!\.(example|sample|dist|template))|id_(rsa|ed25519)|credentials[\s_-]?file|pri…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 pathsscripts/skill_firewall.py:161 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… r"(\bcurl\b|\bwget\b|requests?\.(get|post)|fetch\()[^\n]{0,120}(\.ssh|id_rsa|\.env\b|credentials[\s_-]?file|\.netrc|MEMORY\.md|USER\.md|SOUL\.md|paired\.json)[^\n…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detectedscripts/skill_firewall.py:315 · Unicode escape sequence detected — may contain obfuscated payloadsZERO_WIDTH = re.compile(r"[\u200b\u200c\u200d\u2060\ufeff\u202a-\u202e\u2066-\u2069]")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
Prompt injectionSKILL.md:60 · Prompt injection — known jailbreak technique reference| SF1xx prompt injection | instruction override, jailbreak/role hijack, fake system tags, secrecy directives, system-prompt theft |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsscripts/skill_firewall.py:123 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"~/\.docker/config\.json|\.git-credentials|~/\.netrc|\.npmrc|\.pypirc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionreferences/threat-model.md:28 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| SF102 | Role hijack / jailbreak personas and "no restrictions" framing | HIGH |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionscripts/skill_firewall.py:163 · File type combined with upload action — agent may exfiltrate local data filesr"(\.ssh|id_rsa|\.env\b|credentials[\s_-]?file|\.netrc|MEMORY\.md|USER\.md|SOUL\.md|paired\.json)[^\n]{0,120}(\bcurl\b|\bwget\b|upload|exfiltrat|webhook|telegram|discord|pastebin|\bsend\b|--data)",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
≈1,695 tok
1 file · 4 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

32 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim thiennhant95: 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. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim thiennhant95Propose a patch to the maintainer