course-followup-sequence

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified during the analysis of the skill instructions and workflow.
  • [COMMAND_EXECUTION]: The skill involves generating text and saving it to local markdown files (e.g., followup-d[N]-review-request.md). This is consistent with its stated purpose of automating follow-up copy assets and does not involve high-risk command execution or privilege escalation.
  • [DATA_EXPOSURE]: There is no evidence of sensitive data exposure or exfiltration. The skill operates on user-provided course and instructor information to generate marketing and follow-up copy.
  • [PROMPT_INJECTION]: The skill uses a multi-step chain of vendor-provided tools (copywriting, slop-reviewer, spell-check) to process user input. While this represents an indirect prompt injection surface as it ingests untrusted user text, the use of a review chain and the limited capability (writing local markdown files) minimizes risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:35 PM
Security Audit — agent-trust-hub — course-followup-sequence