Pamela Calls

Make AI phone calls instantly. No lag, no setup, unlimited scale.

This skill appears coherent for its stated purpose, but take these precautions before installing or providing credentials: - Use a restricted or test API key (not a full production key) while trying the skill. The provider documentation itself recommends this. - Be aware that calls are billable ($0.10/min according to the docs); the agent invoking the skill can place live outbound calls that generate charges. Enable billing alerts and monitor usage. - Verify package names and domains to avoid typosquatting (e.g., @thisispamela on npm, thisispamela on PyPI, docs.thisispamela.com / thisispamela.com). Confirm these packages exist and are maintained by the vendor before installing. - If you accept webhooks, implement signature verification (X-Pamela-Signature) as the docs recommend to prevent forged events, and avoid posting webhooks to public/untrusted endpoints. - Do not store production API keys in public configs, logs, or shared repositories. Rotate keys if they are exposed. If you want higher assurance, check the vendor identity (thisispamela.com), inspect the actual npm/PyPI packages and their source repos, and test with a restricted billing account before enabling this skill in production.

Type: OpenClaw Skill Name: pamela-call Version: 1.1.12 The skill bundle describes an AI phone call service, Pamela, and provides documentation for its usage, including API key requirements and SDK installation. The `SKILL.md` transparently discloses data handling (call audio/transcripts sent to Pamela) and includes a 'Trust & security' section advising on best practices and warning against typosquatting. There is no evidence of intentional malicious behavior, prompt injection with harmful objectives, unauthorized data exfiltration beyond the stated purpose, or attempts to install backdoors or execute arbitrary remote code. All instructions and code examples are aligned with the stated purpose of interacting with the Pamela API.