building-journalist-outreach-list-from-twitter

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to execute a local script scripts/run_actor.js and curl for interacting with the Apify REST API. These are standard methods for the skill's stated purpose of data collection from a cloud platform.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with api.apify.com to trigger scraping tasks and retrieve results. This is the primary function of the skill and targets a well-known service infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Twitter bios and tweets). It includes a filtering step (Step 4) to identify journalist signals, which acts as a basic validation layer for the ingested content, though the category is inherently present due to the ingestion of untrusted external text.
  • [SAFE]: The resources and tools referenced (Apify actors apidojo/twitter-user-scraper and apidojo/tweet-scraper) are provided by the skill author (apidojo-io), representing a legitimate use of the author's own infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:53 PM
Security Audit — agent-trust-hub — building-journalist-outreach-list-from-twitter