twitter-thread-creation

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its use of tools that ingest external data.
  • Ingestion points: Processes untrusted data from external websites via infsh/agent-browser and search results via tavily/search-assistant in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided thread-creation templates.
  • Capability inventory: The skill possesses the capability to post content to social media (x/post-create), which could be leveraged to perform unauthorized actions if the agent is manipulated by instructions hidden in external content.
  • Sanitization: There is no evidence of content sanitization or validation of the results returned by the browsing and search tools before they are used for content generation.
  • [EXTERNAL_DOWNLOADS]: Fetches installation guidelines for the infsh CLI from the vendor's official GitHub repository.
  • [COMMAND_EXECUTION]: Executes shell commands via the infsh CLI to post tweets, generate images from HTML, and perform automated browser tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 07:30 PM