ClawAudit verdict

rune-kit

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Skill is an index/mesh for a collection of 64 development skills organized in a layered architecture; it contains only installation instructions and an architecture overview with no malicious patterns.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
70
transparency
70
maintenance

Findings (27)

Pattern match critical

Pipe to bash — executes piped content as shell commands

skills/rune-completion-gate.md · code · | Bash

Pattern match critical

Prompt injection — tries to override agent instructions

skills/rune-ext-ai-ml.md · code · ignore previous instructions

Pattern match critical

Uses eval() — can execute arbitrary code

skills/rune-integrity-check.md · code · eval(

Pattern match critical

<script> tag in markdown — potential code injection

skills/rune-skill-forge.md · code · <script>

Pattern match high

Instructs covert action — may act without user awareness

skills/rune-audit.md · code · silently

Pattern match high

Uses spawn() — can execute external programs

skills/rune-ext-ai-ml.md · code · spawn(

Pattern match high

Pipe to python — executes piped content as Python code

skills/rune-doc-processor.md · prose · downgraded · | Python

Pattern match high

References child_process — can spawn system processes

skills/rune-ext-ai-ml.md · code · child_process

Pattern match high

Uses exec() — may execute shell commands

skills/rune-ext-ai-ml.md · code · exec(

Pattern match high

Dynamic import() — loads module at runtime

skills/rune-ext-content.md · code · import('

Pattern match high

Accesses system credential store

skills/rune-ext-mobile.md · code · keychain

Pattern match high

Accesses sensitive system files

skills/rune-ext-security.md · prose · downgraded · /etc/passwd

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

skills/rune-ext-security.md · prose · downgraded · curl | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

skills/rune-ext-security.md · prose · downgraded · | sh

Pattern match high

Recursive delete from root or home — destructive command

skills/rune-sentinel.md · prose · downgraded · rm -rf /

Pattern match medium

References agent configuration files

skills/rune-docs.md · code · CLAUDE.md

Pattern match medium

References agent memory files

skills/rune-cook.md · code · memory.md

Pattern match medium

Opens WebSocket connection

skills/rune-ext-ai-ml.md · code · WebSocket

Pattern match medium

Accesses sensitive environment variables

skills/rune-ext-content.md · code · process.env.ALGOLIA_ADMIN_KEY

Pattern match medium

References sudo — requests elevated privileges

skills/rune-sentinel-env.md · prose · downgraded · sudo

Pattern match medium

Popular HTTP library — network access

skills/rune-hallucination-guard.md · code · axios

Pattern match medium

References tunneling service

skills/rune-ext-zalo.md · code · ngrok

Pattern match medium

Blob URL — may embed executable content

skills/rune-graft.md · code · blob:

Pattern match medium

subprocess execution — runs system commands from Python

skills/rune-sentinel-env.md · prose · downgraded · subprocess.run(

Pattern match medium

Deno.Command — spawns subprocess in Deno runtime

skills/rune-sentinel-env.md · prose · downgraded · Deno.Command

Pattern match low

Makes HTTP request to external URL

skills/rune-ext-content.md · code · fetch('https://

Pattern match low

Base64 encoding/decoding

skills/rune-ext-saas.md · prose · downgraded · base64decode

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API