seo-drift
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
../../scripts/compare_snapshots.pyto process and compare SEO snapshots. This script execution is part of the core functionality defined in the workflow of SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external website data which presents a surface for indirect prompt injection attacks.
- Ingestion points: External source HTML, SEO snapshots, and exports are loaded as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the loaded evidence.
- Capability inventory: The agent can execute a Python comparison script (SKILL.md) and read multiple referenced files.
- Sanitization: There is no mention of sanitizing or escaping the HTML content before it is processed by the agent or the script.
Audit Metadata