cerbos-authz-migration
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze arbitrary source code and configuration files to extract authorization intent, which presents a surface for indirect prompt injection.
- Ingestion points: The skill analyzes project files such as API handlers, policy files, and database schemas (e.g., Phase 1 and 2 in SKILL.md and DISCOVERY.md).
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions that may be embedded within strings or comments in the analyzed code.
- Capability inventory: The agent uses extracted data to generate migration specs, mapping constructs, and shadow plans; it does not perform command execution on the ingested data.
- Sanitization: No sanitization or escaping of the ingested code content is specified in the instruction set.
Audit Metadata