The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell commands via npx agentcash@latest to manage wallet balances, discover API endpoints, and perform authenticated fetch requests.
[EXTERNAL_DOWNLOADS]: The skill communicates with multiple external origins for its primary functionality, including agentcash.dev, stableenrich.dev, stablesocial.dev, stablestudio.dev, stableupload.dev, stableemail.dev, stablephone.dev, stablejobs.dev, and stabletravel.dev.
[REMOTE_CODE_EXECUTION]: The skill uses npx to download and execute the latest version of the agentcash package from the npm registry at runtime.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it instructs the agent to read and follow an instructions field returned by the discover command from external, potentially untrusted service origins.
Ingestion points: The agent ingests data from external origins via the npx agentcash@latest discover <origin> command as described in SKILL.md.
Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the ingested data.
Capability inventory: The skill has the capability to execute shell commands (npx), perform network operations (fetch), upload files (stableupload.dev), send emails (stableemail.dev), and initiate phone calls (stablephone.dev).
Sanitization: There is no evidence of sanitization or validation of the content received from the instructions field before the agent processes it.

agentcash