Caveat verdict

agentphone

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND makes external network calls

The skill provides a legitimate way for AI agents to make phone calls. It does not contain any malicious code or intent.

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.

25
security
90
transparency
90
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

Findings (5)

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

POSTs data to external URL

SKILL.md · code · .post("https://

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.AGENTPHONE_API_KEY

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

Requires 1 environment variable. (1 sensitive: [AGENTPHONE_API_KEY]). Requires 1 system binary.

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