forensic-review
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted data from implementation phases, creating an indirect prompt injection surface.
- Ingestion points: The skill reads task assignments, expected implementation files, and success conditions via MCP tools like
sam_taskandartifact_readin SKILL.md. - Boundary markers: No specific delimiters or safety warnings are instructed for handling the external implementation data within the agent's context.
- Capability inventory: The skill has the ability to update task records and trigger remediation task creation using
sam_task(action='update')as seen in SKILL.md. - Sanitization: The instructions do not specify any validation or sanitization procedures for the code review artifacts or implementation files before they influence the pipeline's verdict logic.
Audit Metadata