all-noindex-pages
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to audit rendered HTML, structured data, and HTTP response headers from external or project pages. This creates a surface for indirect prompt injection if the processed content contains malicious instructions. However, this data processing is essential to the skill's primary function of SEO auditing.
- Ingestion points: Rendered HTML and HTTP response headers are identified as the primary data sources in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat audited content as untrusted data.
- Capability inventory: The skill's scope is limited to reviewing metadata and flagging routes; it does not invoke dangerous capabilities like network exfiltration or persistent file system modifications.
- Sanitization: No specific sanitization or filtering of the audited HTML or header content is defined in the instructions.
Audit Metadata