programmatic-seo

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill body directs the agent to read and adopt a workflow from a relative file path (../../seo/programmatic-seo/SKILL.md), establishing an instruction ingestion surface.
  • Ingestion points: The instructions in SKILL.md explicitly command the agent to read ../../seo/programmatic-seo/SKILL.md and follow it as the active workflow.
  • Boundary markers: No explicit delimiters, wrappers, or instructions are provided to the agent to treat the external file content as potentially untrusted or to restrict its influence.
  • Capability inventory: The skill's stated purpose involves SEO auditing and planning for large-scale generated pages, which implies the availability of tools for file system interaction and content analysis.
  • Sanitization: The skill lacks any mechanism to validate, filter, or sanitize the content of the referenced file before the agent adopts its instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 04:16 PM