Ressemble TTS e STT
Analysis
This skill appears to do what it claims—send text or audio to Resemble AI for speech generation/transcription—but users should notice the external API and API-key requirements.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
It uses direct HTTP calls to Resemble's production endpoints and supports asynchronous transcription polling.
The skill clearly discloses that it contacts Resemble AI over HTTP; this is expected for TTS/STT, but user text and audio may leave the local environment.
requires:
bins: ["curl", "jq", "base64"]
env: ["RESEMBLE_API_KEY"]The included skill file declares required binaries and an API key, while the registry-level requirements list no required binaries or environment variables. This is an under-declared setup requirement rather than evidence of hidden behavior.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
env: ["RESEMBLE_API_KEY"]
primaryEnv: "RESEMBLE_API_KEY"The skill requires a Resemble API key for provider access. This is purpose-aligned, but it grants delegated access to the user's Resemble account.
