issue-triage

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data from customer support issues.
  • Ingestion points: Support ticket content and communication threads described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or warnings to separate ticket content from instructions.
  • Capability inventory: No code, command execution, or network tools are present or referenced within this skill.
  • Sanitization: No input validation or sanitization logic is specified.
  • [NO_CODE]: The skill consists entirely of instructional text and documentation. It does not include any scripts, executable files, or tool configurations that could be used for malicious purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:06 PM
Security Audit — agent-trust-hub — issue-triage