create-github-issues-feature-from-implementation-plan

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it instructs the agent to analyze and act upon the contents of an external file.
  • Ingestion points: Data is read from the implementation plan file path specified in the ${file} variable.
  • Boundary markers: Absent. No instructions are provided to delimit the plan data or to ignore instructions embedded within the file content.
  • Capability inventory: The skill utilizes GitHub-related tools including 'search_issues', 'create_issue', and 'update_issue'.
  • Sanitization: Absent. No validation or sanitization of the file content is performed before the data is used to populate issue fields.
  • [NO_CODE]: The skill consists entirely of markdown instructions and metadata without any accompanying scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:20 AM
Security Audit — agent-trust-hub — create-github-issues-feature-from-implementation-plan