Caveat verdict
skill-release-plus
Executes processes AND makes external network calls
This skill packages and publishes skills to documented hubs (ClawHub, skillhub.cn, GitHub Releases) using declared API tokens; the user-hook adapter system is transparent and the overall purpose is legitimate skill distribution tooling.
Automated static analysis — not a human review. Caveat 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 Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
network_out
package_install
Findings (5)
Possible hardcoded credential
scripts/release.py · prose · downgraded · token: "
f
subprocess execution — runs system commands from Python
scripts/_adapter_clawhub.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
scripts/_adapter_github_release.py · prose · downgraded · urllib.request
Sets world-executable permissions
scripts/_lib_config.py · prose · downgraded · chmod 700
Python os.environ.get — reads environment variable
scripts/_lib_package.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D/F). 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.
package_installprocess_execnetwork_out Thanks — recorded.