create-github-issue-feature-from-specification

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes external specification files (${file}) to extract requirements for GitHub issues. This behavior creates a risk of indirect prompt injection where malicious instructions embedded in the specification file could influence the agent's behavior during the issue creation or update process.
  • Ingestion points: Input specification file (${file}) processed in step 1.
  • Boundary markers: None present; the instructions do not specify using delimiters or ignore-instructions warnings for the file content.
  • Capability inventory: search_issues, create_issue, and update_issue tools are used to interact with GitHub based on the processed content.
  • Sanitization: No evidence of sanitization, validation, or escaping of the specification file content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 05:25 AM