The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local helper script (run_superagent.mjs) using the Node.js runtime to facilitate streaming AI conversations. The execution is scoped to the skill's primary function of API interaction.
[EXTERNAL_DOWNLOADS]: The skill is distributed via the Felo-Inc GitHub organization. Installation instructions leverage the npx utility to fetch the skill, which is a standard distribution method for this ecosystem.
[CREDENTIALS_SAFE]: Authentication is handled securely by requiring the FELO_API_KEY to be set as an environment variable, preventing the exposure of credentials in the source code or command history.
[DATA_EXFILTRATION]: The skill transmits user queries to the legitimate vendor endpoint https://openapi.felo.ai. This is the intended behavior of the tool and is performed over secure HTTPS connections.
[PROMPT_INJECTION]: The skill features a potential surface for indirect prompt injection (Category 8) as it processes user input directly into a command-line argument for the SuperAgent script. Ingestion point: User query interpolation in SKILL.md. Boundary markers: None explicitly defined. Capability inventory: Execution of local scripts via the bash tool. Sanitization: Not specified in the instructions, relying on the platform's default safety controls.

felo-superAgent