launch

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a feature to generate changelogs and marketing drafts by reading external, potentially untrusted pull request descriptions and commit messages.
  • Ingestion points: Pull request titles, descriptions, and commit logs from a product repository as described in references/shipped-changes.md.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded within the git logs.
  • Capability inventory: The agent uses the ingested data to generate text output (blog posts, emails, changelogs); no dangerous capabilities such as arbitrary file writing or outbound network requests are triggered by this process.
  • Sanitization: Absent; the skill does not specify any validation or filtering of the content read from the repository.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to use git log to fetch recent changes. This is a read-only command used strictly for information gathering to support the changelog generation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 09:16 PM