northstar-typescript-audit
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 external source code for auditing and repair. This presents a surface for indirect prompt injection, where malicious instructions embedded in the target code could potentially influence the agent's repair actions or instructions.
- Ingestion points: The skill treats input after the command as the "target and requested worktree or repository scope" in
SKILL.md. - Boundary markers: No explicit prompt delimiters or "ignore embedded instructions" warnings are defined in this entry point to isolate the external source code from the agent's audit logic.
- Capability inventory: The skill performs "audit and repair," which involves reading local files and potentially writing modifications to the worktree (
SKILL.md). - Sanitization: No sanitization, validation, or filtering of the ingested source code is described in this specific component.
Audit Metadata