The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform a curl POST request to a local service (http://localhost:8791/api/agent/batch-scan). This command is used to trigger a secondary automated process for scanning job openings at the identified companies and does not interact with external untrusted servers.
[PROMPT_INJECTION]: The skill processes untrusted data from the web via the WebFetch tool to generate company scores and summaries.
Ingestion points: External career pages and job board data (Greenhouse, Ashby, Lever, etc.) are fetched and parsed.
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for handling the content returned from the web.
Capability inventory: The agent has the ability to perform file writes (Write, Edit) and execute shell commands (Bash).
Sanitization: There are no instructions to sanitize or escape data fetched from the web before it is written to the local target-companies.yaml file, creating a potential surface for indirect prompt injection if malicious content is present on a fetched page.

generate-targets