diff-inspector
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code diffs and PR content provided by users or retrieved from a repository, creating a surface for indirect prompt injection.
- Ingestion points: User-provided diffs, pasted code snippets, or diffs read from the local Git worktree/repository (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions embedded within the code comments or content of the diff itself.
- Capability inventory: The skill has access to sensitive tools such as
Bash,Write, andEdit(SKILL.md). A successful injection within a diff could attempt to trick the agent into executing arbitrary shell commands or modifying files outside the intended review scope. - Sanitization: There is no evidence of sanitization, escaping, or strict schema validation for the diff content before it is processed by the agent.
Audit Metadata