seo-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external websites by fetching a user-supplied URL. This functionality creates an attack surface for indirect prompt injection if the crawled site contains hidden instructions intended to manipulate the agent. However, the risk is minimal because the skill is strictly limited to generating a markdown strategy report and lacks high-risk capabilities such as arbitrary command execution, file system access, or network exfiltration.
- Ingestion points: The intake workflow fetches site content from the URL provided by the user (documented in SKILL.md).
- Boundary markers: None defined to encapsulate external content.
- Capability inventory: Restricted to text generation; no evidence of subprocess calls, file writes, or data transmission tools.
- Sanitization: No specific content filtering or sanitization protocols are documented.
- [SAFE]: The workflow logic and reference materials are consistent with legitimate marketing and SEO professional practices. All external links point to well-known search engines, SEO tools, and reputable educational content. No evidence of obfuscation, hardcoded credentials, or unauthorized persistence mechanisms was found.
Audit Metadata