The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes curl via Python's subprocess and shell scripts to fetch content from the Jina.ai Reader API. This is the primary function of the skill and is implemented with basic URL validation.\n- [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from external Twitter/X URLs, which is then processed by the agent. This content could contain instructions designed to manipulate the agent's behavior.\n
Ingestion points: scripts/fetch_tweet.py and scripts/fetch_tweets.sh retrieve external content from URLs.\n
Boundary markers: The skill does not use delimiters or warnings to isolate fetched content.\n
Capability inventory: The agent has access to shell commands and file writing tools.\n
Sanitization: Fetched content is not sanitized before being passed to the agent.

twitter-reader