findings-to-github-issues

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed purely for text formatting into markdown templates. It does not perform API calls or authentication.
  • [NO_CODE]: No executable scripts, shell commands, or external package dependencies are present in the skill definition.
  • [PROMPT_INJECTION]: The skill processes external findings, which represents an indirect prompt injection surface.
  • Ingestion points: The skill accepts a list of findings to be formatted (SKILL.md).
  • Boundary markers: No explicit delimiters are defined to isolate input data from instructions.
  • Capability inventory: Functionality is limited to text formatting; no dangerous capabilities like code execution or network access are present.
  • Sanitization: No validation or sanitization of input findings is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:40 PM
Security Audit — agent-trust-hub — findings-to-github-issues