traffic-drop
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for a specific analytical task and uses a defined set of tools to process SEO data. No evidence of malicious intent or harmful patterns was found.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from an external source.
- Ingestion points: Tool outputs containing query strings, page URLs, and descriptions from SKILL.md.
- Boundary markers: The instructions do not define specific delimiters to separate untrusted data from the system prompt.
- Capability inventory: The skill includes the create_annotation tool, which allows writing data back to the external property, though this is mitigated by a required user confirmation step.
- Sanitization: There is no evidence of data sanitization or filtering for the external inputs before they are included in the agent's context.
Audit Metadata