The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, including Twitter feeds (KOL tweets), news titles, and RSS feeds, which are ingested via the api.ctmon.xyz API. This content is interpolated into the agent's context for synthesis and reporting. The lack of explicit boundary markers or instructions to ignore embedded commands creates a risk that malicious instructions within the fetched data could influence the agent's behavior.
Ingestion points: External data enters the agent context through endpoints such as /tweets/feed, /info/feed, and /twitter/realtime as seen in SKILL.md.
Boundary markers: The prompt templates provided in the 'Combos' sections do not utilize clear delimiters or instructions to prevent the agent from obeying instructions found within the data.
Capability inventory: The skill utilizes curl and jq for data processing, and provides instructions for using openclaw cron to automate tasks.
Sanitization: There is no evidence of sanitization or filtering of the remote content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using curl and jq to interact with the vendor's API. While these are used for the intended purpose of the skill, they represent the execution of local binaries based on parameters defined in the instructions.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data from https://api.ctmon.xyz/api. This is the primary functionality of the skill and targets the author's infrastructure, but it involves downloading and processing external content at runtime.

ct-monitor