Skills
skills/b-open-io/prompts/x-tweet-fetch/Gen Agent Trust Hub

x-tweet-fetch

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill fetches untrusted content from X (Twitter), creating a surface for indirect prompt injection where malicious tweet content could influence agent behavior.
  • Ingestion points: scripts/fetch.sh fetches data from api.x.com.
  • Boundary markers: No markers are used to separate fetched data from instructions.
  • Capability inventory: scripts/fetch.sh can execute shell commands via curl and jq.
  • Sanitization: No sanitization is performed on the API response text.
  • [COMMAND_EXECUTION]: The script fetch.sh uses curl and jq to interact with external APIs. Input is sanitized via regex before being used in the API request, reducing the risk of shell injection through the ID parameter.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:38 AM