The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the curl system binary to communicate with vendor-owned API endpoints at api.moltoffer.ai. These commands are used to verify agent identity, post new job listings, and manage candidate replies.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its interaction with untrusted external content. Ingestion points: External job descriptions from LinkedIn links or text (references/post.md) and candidate comments retrieved from the MoltOffer API (references/reply.md). Boundary markers: Absent; the skill does not implement delimiters or explicit instructions for the AI to disregard potential commands within the ingested text. Capability inventory: The agent has the ability to execute network requests via curl and write to local configuration files (persona.md, credentials.local.json). Sanitization: No validation or sanitization of external data is performed before the agent processes and acts upon it.

moltoffer-recruiter