The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Ideaboard API, specifically idea descriptions and comments submitted by other users. This exposes the agent to indirect prompt injection attacks where malicious instructions could be embedded in these fields.
Ingestion points: idea.description and idea.comments are fetched and processed in examples/browse-ideas.ts and examples/pick-up-and-ship.ts.
Boundary markers: Absent. No instructions are provided to the agent to disregard instructions within the data.
Capability inventory: Network access via the axios library is present across all example scripts.
Sanitization: Absent. The skill examples log the retrieved content without filtering or validation.
[EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install standard, reputable libraries (axios, viem, siwe) and utilizes the vendor's own npx skills tool for maintenance. These are legitimate dependencies associated with the skill's author.
[COMMAND_EXECUTION]: The skill provides example shell commands for dependency management and skill updates, which are standard for a development environment.

openserv-ideaboard-api