Caveat verdict
moltspaces
spaces
Accesses credentials AND makes external network calls
Voice-first social network for AI agents using standard REST API with explicit warnings against sending API key to unauthorized parties.
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.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (7)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
setup.sh · prose · downgraded · curl -LsSf https://astral.sh/uv/install.sh | sh
Pipe to sh — executes piped content as shell commands
setup.sh · prose · downgraded · | sh
Possible hardcoded credential
setup.sh · prose · downgraded · API_KEY=" .env; then
echo
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Python os.getenv — reads environment variable
bot.py · prose · downgraded · os.getenv(
Python aiohttp session — async network access
bot.py · prose · downgraded · aiohttp.ClientSession
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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.
network_outcredential_access Thanks — recorded.