competitor-seo-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from external competitor pages and data exports.
- Ingestion points: The instructions specify collecting user pages, listing exports, and competitor content from external URLs or provided datasets in SKILL.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the analyzed content to prevent the agent from following malicious commands hidden in the data.
- Capability inventory: The skill is primarily designed for data comparison and reporting; no high-risk capabilities such as arbitrary shell command execution or local file system modifications were identified in the provided files.
- Sanitization: The workflow does not include steps to sanitize or filter input from external sources before it is processed by the agent.
Audit Metadata