monitoring-brand-mentions-on-twitter
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Twitter/X search results (tweet text, author handles, and URLs) and processes it for sentiment analysis and reporting.
- Ingestion points: Fetches data from Twitter via Apify actors (
apidojo/tweet-scraper) in Step 2 and Step 3. - Boundary markers: None identified in the instructions for isolating external tweet content.
- Capability inventory: The skill uses
curlfor network requests andnodeto execute local scripts (run_actor.js). - Sanitization: No specific sanitization or filtering of tweet content is mentioned before it is processed by the agent or output in the final report.
- [DYNAMIC_EXECUTION]: The
customMapFunctioninput parameter accepts a raw JavaScript function string intended to transform output objects. While this is a common feature in data processing tools, it represents a dynamic execution surface if the agent allows the execution of this user-supplied code. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.apify.comto run scrapers and retrieve datasets. These requests use theAPIFY_TOKENprovided by the user. - [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using
nodeandcurlto interact with the Apify API and local scripts. These commands include environment variable usage ($APIFY_TOKEN,$RUN_ID) and parameter interpolation.
Audit Metadata