scanning-product-with-sfdipot
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing untrusted external data including project requirements documents (PRD), code, logs, and architectural diagrams. There are no instructions for sanitizing this input or using boundary markers to prevent the agent from executing instructions that might be embedded in these external sources. * Ingestion points: Processes external materials like PRDs, business rules, prototypes, interfaces, architecture, code, configuration, logs, and history (SKILL.md). * Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the analyzed content. * Capability inventory: The skill involves reading local files such as test-privateer/references/artifact-routing.md (SKILL.md). * Sanitization: No sanitization or validation logic is specified for the external content being processed.
Audit Metadata