The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external job specifications and marketplace listings, which creates a vulnerability surface for indirect prompt injection attacks.
Ingestion points: The skill fetches job details and categories using t2 job board and t2 job spec <jobId> as described in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present to protect the agent from acting on malicious text within job descriptions.
Capability inventory: The skill uses the t2 CLI for critical actions including connecting wallets (t2 connect), claiming jobs, and delivering files (t2 job deliver), which could be misused if the agent is influenced by malicious job data.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the marketplace before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of external components from the vendor's ecosystem.
Node.js package: Instructions specify the installation of @t2000/cli via npm install -g.
Skill dependencies: The skill installs additional functionality from the t2000-afi/t2000-skills repository using npx skills add.
[COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of shell commands using the t2 CLI tool.
Execution patterns: Commands are used to manage connections (t2 connect), browse jobs (t2 job board), and submit work (t2 job deliver), relying on the underlying environment's shell for execution.

t2000-earn