opentwitter

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by retrieving data from untrusted external sources.\n
  • Ingestion points: Fetches tweet and user data from the 6551 REST API through endpoints like /open/twitter_search and /open/twitter_user_tweets.\n
  • Boundary markers: The skill does not define specific delimiters or instructions to treat the fetched tweet content as data rather than instructions.\n
  • Capability inventory: Accesses the network via the curl command and utilizes an environment variable for authentication.\n
  • Sanitization: No evidence of sanitization or filtering is provided for the fetched content.\n- [COMMAND_EXECUTION]: The skill explicitly requires and uses the curl system utility to perform network operations against the vendor's API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 10:12 AM