agent-native-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases to identify architectural gaps, creating a surface for indirect prompt injection where malicious instructions hidden in the codebase could attempt to influence the agent's logic.
- Ingestion points: The skill utilizes
Read,Grep, andGlobtools to ingest arbitrary content from the project's source files inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the content read from files.
- Capability inventory: The skill is permitted to use
Bash,Read,Grep, andGlob, which provide an execution and data access surface if the agent is manipulated by injected content. - Sanitization: There is no mention of sanitizing or escaping the content retrieved from the codebase before the agent processes it.
Audit Metadata