The Agent Skills Directory

[DATA_EXFILTRATION]: The skill provides instructions for the agent to read and display the contents of the configuration file located at ~/.config/rssaurus/config.json. This file typically contains the user's API tokens and authentication secrets, which are then exposed directly to the agent's context.
[COMMAND_EXECUTION]: The skill utilizes the rssaurus command-line utility to perform various tasks, including listing feeds, retrieving items, and opening URLs from the terminal.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of external data:
Ingestion points: The agent retrieves untrusted content from external RSS feeds using the rssaurus items command mentioned in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to ensure the agent ignores or treats the retrieved feed content as data rather than instructions.
Capability inventory: The skill allows for shell command execution via the rssaurus binary and local file reading using the cat command.
Sanitization: The skill does not implement any validation or sanitization of the content fetched from external RSS sources before it is processed by the agent.

rssaurus-cli