twitter-intel

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from Twitter which is then processed by an LLM, creating an indirect prompt injection surface.
  • Ingestion points: The skill fetches tweets via the search API in Phase 1 and reads from daily JSON files in Phase 3 (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when passing tweet text to the LLM.
  • Capability inventory: The skill uses an LLM to categorize themes and generate narratives based on collected tweets (Phase 3).
  • Sanitization: No sanitization or filtering logic is mentioned to prevent malicious tweet content from influencing the LLM's output.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the rnet Python package from the public PyPI registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:57 PM