twitter-profile-lookup
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to export environment variables and parses local JSON configuration files using Python's built-in modules.
- [EXTERNAL_DOWNLOADS]: The documentation specifies the use of
npxto download and run vendor-specific tools for installation and authentication. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Twitter/X profiles and tweets, which serves as a potential attack surface for indirect prompt injection.
- Ingestion points: External data enters through the Scrape Creators API proxy via Twitter profiles and user tweets.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the provided shell commands.
- Capability inventory: The skill performs network operations using
curland manages local environment variables. - Sanitization: There is no evidence of sanitization or validation performed on the external content before it is processed by the agent.
Audit Metadata