twitter-profile-lookup

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via python3 -c to dynamically parse JSON content and extract configuration values from the local file system.
  • [DATA_EXFILTRATION]: The skill accesses the local configuration file ~/.gooseworks/credentials.json to harvest an API key and base URL, which are subsequently transmitted in the authorization headers of network requests to api.gooseworks.ai and api.orth.sh.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8).
  • Ingestion points: Retrieves untrusted data, including user biographies and tweet content, from external Twitter/X profiles via the Scrape Creators API.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the retrieved social media content as untrusted data.
  • Capability inventory: The skill uses curl for network operations and shell execution to manage environment variables.
  • Sanitization: There is no evidence of content filtering or sanitization performed on the fetched Twitter data before it is integrated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 06:18 AM
Security Audit — agent-trust-hub — twitter-profile-lookup