Caveat verdict
crypto-daily-report
Accesses credentials AND makes external network calls
The skill reads a token from `~/.openclaw/.env` using shell grep and sends data to hardcoded Telegram IDs (chatId: 680162114, threadId: 182747); while this matches the described purpose of sending a daily report, the hardcoded destination IDs and silent-execution principle (NO_REPLY after sending) create an ambiguous exfiltration-like pattern for an automated skill.
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 (4)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/.env
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | python3
Instructs covert action — may act without user awareness
skill-card.md · prose · downgraded · silently
Python urllib.request — network access
scripts/fetch_defi_yields.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Thanks — recorded.