fix-my-twitter-profile

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Twitter profiles, creating a vulnerability surface where malicious instructions embedded in a user's bio or tweets could potentially influence the agent's behavior.\n- Ingestion points: Twitter profile fields including Name, Bio, and Pinned Tweet as described in Steps 2, 3, and 4.\n- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the profile content being analyzed.\n- Capability inventory: The skill involves content generation (bio rewrites) and calls specialized analysis tools such as get_voice_profile and score_voice_match.\n- Sanitization: No input validation or sanitization is specified for the data ingested from the profiles.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:24 AM