Caveat verdict
nadfun
Accesses credentials AND makes external network calls
NadFun decentralized token launchpad integration skill covering trading, token creation, and event indexing on Monad blockchain; uses standard viem library for on-chain interactions with user-controlled credentials.
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
package_install
Findings (6)
Possible hardcoded credential
AGENT-API.md · code · API_KEY = "nadfun_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · > **Note:** To obtain an API key, you must first login to [nad.fun](https://nad.fun) via wallet signature. See the [Authentication](#authentication-login-flow)
Accesses sensitive environment variables
TOKEN.md · code · process.env.PRIVATE_KEY
fetch() — outbound network request
SKILL.md · code
Contains shortened/invite URL
CREATE.md · code · t.me/mytoken
Opens WebSocket connection
INDEXER.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accesspackage_install Thanks — recorded.