The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on a local Node.js script (scripts/cli.mjs) to perform all data retrieval and platform interaction tasks. The agent is instructed to run commands like node cli.mjs search-articles and node cli.mjs get-article to fetch information from the PANews platform.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which could be exploited to influence agent behavior through indirect prompt injection.
Ingestion points: The skill retrieves full article content in workflow-read-article.md and community-generated comments in workflow-topics.md.
Boundary markers: There are no explicit instructions or delimiters defined to isolate external data from the agent's internal reasoning or to warn the agent to ignore instructions embedded in the news content.
Capability inventory: The agent has the capability to execute local CLI commands (node scripts/cli.mjs) which are used to fetch and display the external data.
Sanitization: The workflows do not specify any sanitization, filtering, or validation of the retrieved text before it is presented to the agent for summarization or analysis.

panews