trend-discovery

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the @anthropics/bird CLI tool, which is maintained by a trusted organization.- [COMMAND_EXECUTION]: Utilizes standard system commands such as bird search and curl to query APIs and fetch trending content from the web.- [PROMPT_INJECTION]: As the skill is designed to process external data from X, GitHub, and other community sites, it presents a surface for indirect prompt injection.
  • Ingestion points: External data enters the context via the bird search, curl, and web_fetch commands targeting public social and developer platforms.
  • Boundary markers: There are no specific delimiters or instructions defined to isolate the external content from the agent's internal logic.
  • Capability inventory: Capabilities are limited to subprocess execution for data retrieval and network operations to well-known domains.
  • Sanitization: No explicit sanitization or validation logic is applied to the content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 02:15 PM