core-typescript
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's 'Review' mode involves processing and analyzing external code diffs provided by users. This establishes a surface for indirect prompt injection, where an attacker could place malicious instructions within code comments or string literals to attempt to manipulate the agent's review output.
- Ingestion points: User-provided code diffs as described in the
Reviewworkflow inSKILL.md. - Boundary markers: The skill instructions do not specify explicit delimiters or 'ignore' instructions for the ingested code.
- Capability inventory: The skill's capabilities are limited to generating text findings; it does not contain logic for file writing or network execution based on the ingested content.
- Sanitization: No sanitization or validation of the input diff is mentioned.
Audit Metadata