suede-site-alchemy
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external web pages and source code from live URLs and repositories, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill workflow instructs the agent to identify and read live URLs and source folders for analysis.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its internal processing logic and potentially malicious instructions embedded in the external pages being audited.
- Capability inventory: The skill directs the agent to perform tasks such as friction audits, copy rewriting, and experiment design, which involve interpreting and acting upon the data found in the external sources.
- Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the external content before it is incorporated into the agent's context.
Audit Metadata