ClawAudit verdict

gcp-fullstack

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Receives external input AND executes processes

A comprehensive GCP development lifecycle agent that explicitly states it never reads or modifies credential files directly, uses env-var references only, and requires user approval before actions; broad capabilities match its stated full-stack orchestration purpose.

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.

security

transparency

maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (5)

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec(

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.TEST_AUTH_TOKEN

Confirmed in code low

fetch() — outbound network request

SKILL.md · code

Pattern match low

Makes HTTP request to external URL

SKILL.md · code · fetch("https://

Permissions & capabilities

No declared permissions — minimal attack surface.

network_innetwork_outcredential_accessprocess_exec

I installed anyway

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