content-repurposer-sms

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified. All instructions are consistent with the skill's stated purpose of content adaptation and social media management.
  • [PROMPT_INJECTION]: The skill instructions are purely task-oriented. No attempts to override agent constraints, extract system prompts, or bypass safety filters were detected. While the skill processes user-provided source content (an indirect injection surface), it contains no malicious logic to exploit this.
  • [DATA_EXFILTRATION]: The skill accesses a local context file (.agents/social-media-context-sms.md) and uses tools like create_post and list_time_slots. These operations are transparent, vendor-attributed, and essential for the skill's functionality, presenting no risk of unauthorized data exfiltration.
  • [COMMAND_EXECUTION]: The skill does not contain shell commands, script executions, or privilege escalation patterns. The mentioned tools are standard platform extensions for the BlackTwist environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 02:23 AM