suede-ops-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because its primary function is to process and synthesize data from diverse operational sources that could be controlled by an adversary.
- Ingestion points: The skill ingests untrusted data from floor-level interviews (Step 1), operational silos including spreadsheets and inboxes (Step 2), and system logs (Step 6).
- Boundary markers: The instructions lack specific requirements for the agent to use delimiters or 'ignore embedded instructions' prompts when processing content from these external sources.
- Capability inventory: The skill is designed to perform data synthesis, friction quantification, and opportunity ranking. While the skill scripts do not explicitly define file-write or network operations, the agent environment may provide these tools to act on the analyzed data.
- Sanitization: There are no instructions provided for sanitizing, escaping, or filtering the external content before it is interpolated into the agent's reasoning process.
Audit Metadata