northstar-agents-review
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text (review targets) which may contain malicious instructions.
- Ingestion points: The instruction in
SKILL.mdto treat text after the command as the review target or question creates an entry point for external data. - Boundary markers: The skill does not explicitly define delimiters or specific instructions for the agent to ignore embedded commands within the target text.
- Capability inventory: The skill file itself contains no code, subprocess calls, or network operations. It explicitly forbids starting workers, creating worktrees, or authorizing execution.
- Sanitization: There are no sanitization or filtering steps defined for the input text.
Audit Metadata