ClawAudit verdict
qa-gate-gcp
Receives external input AND executes processes
Pre-production QA orchestrator for GCP stack that generates test plans and runs validation scripts; env vars are used in generated scripts for their stated purpose (LLM-as-judge, infra validation) and the skill explicitly states it never reads credential files directly.
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.
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.
Receives external input AND executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Permission integrity
network_out
Findings (6)
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Accesses process.env — reads environment variables
SKILL.md · code
Accesses sensitive environment variables
SKILL.md · code · process.env.TEST_AUTH_TOKEN
fetch() — outbound network request
SKILL.md · code
Python os.environ.get — reads environment variable
SKILL.md · prose · downgraded · os.environ.get(
Makes HTTP request to external URL
SKILL.md · code · fetch("https://
Permissions & capabilities
No declared permissions — minimal attack surface.
network_innetwork_outcredential_accessprocess_exec Thanks — recorded.