create-issue-to-rebase-wip

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local git commit history, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The skill reads back prior git commits to extract summaries (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the commit content as data rather than instructions.
  • Capability inventory: The agent uses the gh CLI for GitHub issue creation, executes git rebase for local file system modification, and invokes the draft-commit-message skill.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the commit message content before it is processed or used to generate new commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 09:37 PM
Security Audit — agent-trust-hub — create-issue-to-rebase-wip