Caveat verdict
dm-bot
Accesses credentials AND makes external network calls
Encrypted agent-to-agent messaging skill for the dm.bot platform using end-to-end encryption (X25519 ECDH); all API calls target the declared dm.bot endpoint.
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
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
credential_access
Findings (4)
Base64 decode (atob) — may hide malicious payloads
encryption.md · code · atob(
Base64 encode (btoa) — may obfuscate data exfiltration
encryption.md · code · btoa(
String.fromCharCode — can build strings to evade detection
encryption.md · code · String.fromCharCode
Base64 encoding/decoding
encryption.md · code · Base64Encode
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessdata_encodingnetwork_in Thanks — recorded.