The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation and execution of the agentcash package from the NPM registry. Instructions guide the agent to use npm install -g agentcash and npx agentcash@latest to interact with the service endpoints.
[COMMAND_EXECUTION]: The skill relies on shell command execution to perform all its primary functions, including making calls, buying numbers, and checking status via the agentcash fetch command.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of call transcripts and AI-generated summaries which could potentially contain adversarial instructions.
Ingestion points: Call transcripts and summaries are retrieved from the https://stablephone.dev/api/call/{call_id} endpoint and loaded into the agent's context.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat transcript content as untrusted data.
Capability inventory: The agent can perform subsequent network requests and shell commands based on the information parsed from these transcripts.
Sanitization: The documentation does not specify any sanitization or filtering of the transcript text before it is processed by the agent.

phone-calls