The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from job listings across LinkedIn, Hacker News, and Twitter/X.
Ingestion points: Job descriptions and comments are retrieved via browser tools and APIs in SKILL.md.
Boundary markers: The skill lacks explicit markers or instructions to treat external job descriptions as untrusted content, which could allow malicious postings to influence the agent's scoring or ranking behavior.
Capability inventory: The skill utilizes Bash for network operations and has Write access to local files.
Sanitization: There is no evidence of sanitization or filtering applied to external job content before it is displayed to the user or saved to the local file system.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute curl commands to retrieve job data from the Hacker News Firebase API. This is a functional requirement of the skill.
[EXTERNAL_DOWNLOADS]: Fetches configuration and job data from Hacker News' official Firebase API at hacker-news.firebaseio.com. This is an interaction with a well-known service.

job-search