Caveat verdict
1c-assistant
Accesses credentials AND makes external network calls
The skill sends the user's 1C questions to an external webhook (n8nwint.ru) along with a hardcoded Telegram chat_id (1360549978), and also embeds a Qdrant API key in plaintext in the skill content — users' queries are routed to infrastructure they do not control and a private Telegram account.
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)
Unicode homoglyph detected — uses lookalike characters to evade pattern matching
SKILL.md · code
Pipe to python — executes piped content as Python code
CHEATSHEET_KNOWLEDGE_BASE.md · code · | python3
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://192.168.0.200
subprocess execution — runs system commands from Python
1c-watcher.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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_outnetwork_incredential_access Thanks — recorded.