landmark-regions
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external, potentially untrusted content, which creates a surface for indirect prompt injection.
- Ingestion points: The description in
SKILL.mdspecifies the skill should be used when reviewing "rendered HTML, interactive components, or design-system patterns." - Boundary markers: The instructions do not provide explicit delimiters or "ignore embedded instructions" warnings for the agent to use when processing the HTML markup.
- Capability inventory: No dangerous capabilities such as file system writes, network requests, or code execution were identified in the skill's instructions or the provided reference files.
- Sanitization: There are no specific instructions regarding the sanitization or filtering of the external data before it is processed by the agent.
Audit Metadata