Skills
Navigate
skills/tmakersas/revid-skills/revid-news-to-daily-short/Gen Agent Trust Hub

revid-news-to-daily-short

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a news-fetching feature (fetchNews: true) that allows the underlying service to ingest data from external sources.
  • Ingestion points: Live news content and articles retrieved by the Revid API from the internet (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or "ignore" instructions to protect the agent from malicious content embedded in the fetched news.
  • Capability inventory: The skill possesses capabilities to render video, check project status, and publish content through the Revid MCP server.
  • Sanitization: Sanitization of the untrusted web data is handled by the vendor's API service rather than the skill's local logic.
  • [COMMAND_EXECUTION]: The example testing script uses standard command-line utilities.
  • Evidence: examples/run.sh executes curl to communicate with the API and jq to process the returned JSON data.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates communication with the vendor's API endpoints for video processing.
  • Evidence: Interacts with https://www.revid.ai/api/public/v3/render and https://www.revid.ai/api/public/v3/status in the provided bash script.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 08:04 PM