correctness-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code provided in the project environment, creating a potential attack surface for indirect prompt injection.
- Ingestion points: The agent uses Read, Grep, and Glob tools to ingest content from project files into its context.
- Boundary markers: The instructions lack explicit delimiters or specific directives for the agent to separate code content from instructions, potentially allowing the agent to follow instructions embedded in code comments.
- Capability inventory: The skill is permitted to use the Bash tool, along with Read, Grep, and Glob, which provides a pathway for command execution if an injection occurs.
- Sanitization: No mechanisms for sanitizing, escaping, or validating the external source code are described before the content is processed.
Audit Metadata