Caveat verdict

earnfi-agent-api-x402

x402-earnfi

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill explicitly lists purchasing likes, reposts, followers, raids, comments, and YouTube views as first-class features paid via USDC; coordinating artificial social engagement violates platform terms at scale.

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.

0
security
70
transparency
100
maintenance

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.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.SOLANA_PRIVATE_KEY

Pattern match low

Base64 encoding/decoding

SKILL.md · prose · downgraded · base64-encode

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outcredential_accesspackage_installdata_encodingnetwork_in
Check another skill Browse the registry Auditing your own skills or configs? Use the API