itsol-code-review-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting untrusted content from pull requests, creating a surface for indirect prompt injection. \n- Ingestion points: The agent reads tech notes, PR descriptions, and changed files which are provided by external contributors as part of the review process (SKILL.md). \n- Boundary markers: The instructions do not define specific delimiters or explicit instructions for the AI to ignore embedded commands within the ingested PR data. \n- Capability inventory: The agent has the ability to read files across the repository and trigger various sub-agents to perform specialized review tasks (04-multi-agent-review-gate.md). \n- Sanitization: There are no requirements for the agent to sanitize or escape the content of the pull request before processing it.
Audit Metadata