twitter-x-marketing

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it involves processing data from external sources and local files.\n
  • Ingestion points: The skill retrieves data from the X API via search queries (tweetsRecentSearch) and reads content from user-provided CSV files as described in the API bot example in SKILL.md.\n
  • Boundary markers: There are no explicit delimiters or instructions provided in the code examples to distinguish between system instructions and data retrieved from external sources.\n
  • Capability inventory: The skill provides functions for creating tweets (createTweet), uploading media, and managing threads, which could be misused if malicious instructions are processed from the incoming data.\n
  • Sanitization: No sanitization or validation logic is present in the examples to filter or escape potential prompt injection attacks embedded within the ingested tweet or CSV content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:17 PM