visual-recap

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tools, including git for diff analysis and the GitHub CLI (gh) for interacting with pull requests. These operations are aligned with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as git diff and local YAML architecture definitions to generate summaries. While this represents a data ingestion surface, the skill utilizes clear HTML comment boundary markers (<!-- system-recap:start -->) to isolate the generated content, and the instructions emphasize that the output is informational and non-blocking.
  • [DYNAMIC_EXECUTION]: The skill includes a Node.js utility script (scripts/upsert-recap-block.mjs) used to update PR descriptions. The script employs execFileSync with argument arrays, which is a secure practice that prevents shell-based command injection by avoiding shell interpolation of user-supplied arguments like PR numbers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 03:58 AM
Security Audit — agent-trust-hub — visual-recap