suede-pricing
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external pricing pages and local business context files, which is a standard requirement for its primary purpose but introduces a minor surface for indirect prompt injection.
- Ingestion points: The skill reads
.agents/product-marketing.mdand fetches external pricing page content (SKILL.md,references/pricing-page-teardown.md). - Boundary markers: No explicit delimiters are used to wrap external content.
- Capability inventory: The skill only generates text-based responses and does not have tools for shell execution or network exfiltration.
- Sanitization: No content filtering is applied.
- [DATA_EXFILTRATION]: The skill performs network requests to fetch data from user-specified pricing URLs for analysis.
- Evidence: The teardown workflow requires fetching rendered text or HTML from external sites to score AI-agent readiness and human experience.
Audit Metadata