The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute specific binaries (company-hiring, h1b-hiring) through a bash shell tool provided by the hedwigai MCP. The instructions involve passing user-supplied parameters like role names or company names directly into shell commands.
[INDIRECT_PROMPT_INJECTION]: The skill processes job post data and labor filings which are external, untrusted sources that could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: The skill fetches live job posts from Greenhouse, Lever, and Ashby boards, as well as US labor condition application filings via the company-hiring and h1b-hiring tools.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to separate the fetched external data from the agent's operating instructions.
Capability inventory: The skill utilizes a bash shell tool with jq and the ability to write to the /tmp directory.
Sanitization: There is no mention of sanitization, filtering, or escaping of the content retrieved from job boards or filings before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references the hedwigai MCP server and a plugin marketplace for setup. These resources are associated with the skill's authoring vendor infrastructure.

hiring-signals