seo-programmatic

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute a local script, metadata_template.py, using the claude-seo tool located in the skill's root directory (${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo). This is a vendor-owned resource used for determining site risk based on metadata comparison.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external, untrusted sources such as CSV/JSON files, API endpoints, and database queries. This exposure could allow malicious instructions embedded in the data to influence the agent.
  • Ingestion points: Data assessment functionality in SKILL.md targets CSV/JSON files, API endpoints, and databases.
  • Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from following instructions contained within the external data sources.
  • Capability inventory: The skill utilizes a CLI tool for file-based analysis as described in SKILL.md.
  • Sanitization: No validation or sanitization routines are specified for the incoming data from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 02:25 AM
Security Audit — agent-trust-hub — seo-programmatic