sqli
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase files as input to detect SQL injection, creating an attack surface for indirect prompt injection via malicious code comments.
- Ingestion points: Files matching language-specific patterns in the frontmatter filePattern.
- Boundary markers: None provided in the instructions.
- Capability inventory: The skill uses grep for identification; no network or file-write capabilities are instructed.
- Sanitization: No sanitization logic is included for the ingested code content.
Audit Metadata