create-github-issue-feature-from-specification

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from a specification file which is considered untrusted external data. This creates a surface for indirect prompt injection attacks where malicious instructions embedded within the specification file could potentially override the agent's intended behavior when creating or updating GitHub issues.
  • Ingestion points: Reads and analyzes the specification file provided via the ${file} variable.
  • Boundary markers: Absent. The instructions do not define clear delimiters or provide warnings to the agent to disregard instructions found within the processed data.
  • Capability inventory: The skill utilizes tools to search, create, and update GitHub issues (search_issues, create_issue, update_issue), which involves writing to a remote repository.
  • Sanitization: Absent. There is no mention of escaping or validating the content extracted from the specification file before using it to populate issue titles and descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:19 AM
Security Audit — agent-trust-hub — create-github-issue-feature-from-specification