The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill defines an input parameter customMapFunction described as a "JavaScript function to transform each output object." Accepting executable code as a string input creates a dynamic execution surface that could be exploited if the execution environment is not strictly sandboxed.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from Twitter via a third-party scraper, which can lead to downstream instruction obedience if malicious content is present in the tweets.
Ingestion points: Scraper results from the apidojo/tweet-scraper actor (SKILL.md).
Boundary markers: Absent; there are no specific instructions or delimiters to isolate scraped content from the agent's logic.
Capability inventory: The skill possesses file-writing capabilities (via run_actor.js flags), network access (via curl), and subprocess execution (via node).
Sanitization: No sanitization or filtering logic is specified for the external data before it is presented to the agent or transformed by the mapping function.
[COMMAND_EXECUTION]: The instructions provide shell commands using node to execute local scripts and curl to interact with the Apify REST API. These commands are necessary for the skill's operation but represent a capability that requires oversight.

tracking-sports-team-fan-sentiment-twitter