aggregating-crypto-news

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches cryptocurrency news data from external RSS feeds of well-known organizations such as CoinDesk and The Block. These network requests are required for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill uses Bash to run the local Python-based news aggregator. This command execution is scoped to the crypto:news-* identifier.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources and presents it to the agent without sufficient isolation.
  • Ingestion points: External news data is retrieved in scripts/feed_fetcher.py and parsed in scripts/feed_parser.py.
  • Boundary markers: The skill does not employ specific boundary markers or 'ignore' instructions when providing the aggregated news content to the agent context.
  • Capability inventory: The skill possesses the capability to execute system commands via a scoped Bash tool.
  • Sanitization: Content processing in scripts/feed_parser.py includes basic HTML tag removal but lacks logic to detect or filter malicious natural language instructions embedded in article titles or summaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:55 AM