code-reviewer
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing untrusted code and pull request data, which presents an inherent surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to read pull request descriptions and code files using the
Read,Grep, andGlobtools as part of its core workflow described inSKILL.md. - Boundary markers: While the skill uses a structured workflow and report template, it does not include explicit instructions or delimiters to isolate or ignore instructions that may be maliciously embedded within the code comments or documentation of the reviewed files.
- Capability inventory: The skill's toolset is limited to read-only filesystem operations (
Read,Grep,Glob) and does not possess capabilities for network exfiltration or command execution, limiting the potential impact of an injection. - Sanitization: No explicit input validation or instruction filtering logic is implemented to sanitize the content of the code files before they are processed by the agent.
Audit Metadata