offensive-sqli
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including web endpoint responses, database queries, and application source code, creating a surface for indirect prompt injection.
- Ingestion points: Processes external web endpoints, database queries, and source code files as described in the operational workflow in
SKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or boundary markers to separate untrusted content from the agent's instructions, nor do they include warnings to ignore instructions embedded within the analyzed data.
- Capability inventory: The skill utilizes search tools like
rg(ripgrep) and involves generating remediation code and automated regression tests based on the analyzed data. - Sanitization: There are no documented procedures for sanitizing, escaping, or validating the external content before it is processed by the agent.
Audit Metadata