x-research

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from X.com posts which may contain instructions designed to manipulate agent behavior.
  • Ingestion points: Social media post content and metadata retrieved using browser tools as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are used to separate the extracted content from the agent's instructions.
  • Capability inventory: The skill has access to the Write tool to save research reports to the local filesystem.
  • Sanitization: No sanitization or validation of the ingested tweet content is specified before the synthesis or writing process.
  • Remediation: Surround extracted content with clear delimiters and instruct the agent to ignore any embedded commands within that data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 10:50 PM
Security Audit — agent-trust-hub — x-research