aicoin-news-content

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes news content from external sources.
  • Ingestion points: Article text, headlines, and flash updates are fetched from aicoin.com endpoints via scripts/news.mjs.
  • Boundary markers: No specific delimiters or instructions are used to prevent the agent from interpreting fetched news text as commands.
  • Capability inventory: The script performs network GET requests; the risk involves the agent potentially following instructions embedded in news summaries using its broader set of capabilities.
  • Sanitization: The script does not perform any validation or sanitization of the retrieved text content before returning it to the agent context.
  • [DATA_EXFILTRATION]: The skill uses environment variables AICOIN_ACCESS_KEY_ID and AICOIN_ACCESS_SECRET to authenticate with the vendor's API. This is standard behavior for the intended functionality and follows security best practices for credential management.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 01:44 PM