Caveat verdict

multi-channel-engagement-agent

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

Accesses credentials AND makes external network calls

Autonomous bot that posts replies to Twitter, Farcaster, and Moltbook without per-post user approval; requests crypto private keys (custodyPrivateKey, signerPrivateKey) alongside social API credentials, creating elevated risk for unauthorized social and financial actions.

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
50
transparency
70
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

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

Findings (6)

Pattern match critical

Uses eval() — can execute arbitrary code

references/platform-apis.md · code · eval(

Pattern match medium

References webhook/callback URL

SKILL.md · code · webhookUrl

Pattern match medium

Accesses sensitive environment variables

references/platform-apis.md · code · process.env.PRIVATE_KEY

Pattern match medium

Popular HTTP library — network access

references/reply-strategies.md · code · got

Confirmed in code low

fetch() — outbound network request

SKILL.md · code

Pattern match low

Makes HTTP request to external URL

SKILL.md · code · fetch('https://

Permissions & capabilities

No declared permissions — minimal attack surface.

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