schema-markup-generator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill body contains a directive to "Read [path] completely, then follow it as the active workflow." This pattern instructs the agent to override its current context and adopt rules from an external file, which is an instruction-override pattern.
- Evidence: "Read
../../seo/schema-markup-generator/SKILL.mdcompletely, then follow it as the active workflow." in SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data, specifically URLs or page content, to generate schema markup. This creates a surface for indirect prompt injection if the ingested content contains malicious instructions.
- Ingestion points: Processes external data from a URL or page description provided via the
argument-hintin SKILL.md. - Boundary markers: No specific delimiters or safety instructions are provided to the agent to ignore instructions embedded within the processed content.
- Capability inventory: The skill is designed to process text and generate structured JSON-LD data as described in the frontmatter.
- Sanitization: No evidence of sanitization or filtering of the external input before it is processed by the agent.
Audit Metadata