skills/yaojingang/geohub/seo/Gen Agent Trust Hub

seo

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/run_seo.py) to process SEO requests and generate plans. The script dynamically modifies the Python search path at runtime to include a local src directory to load its core modules.
  • [PROMPT_INJECTION]: The skill processes natural language SEO requests and external evidence data, which creates a surface for indirect prompt injection where malicious instructions could be embedded in the input data.
  • Ingestion points: Natural language requests and input JSON files following the references/input-example.json schema.
  • Boundary markers: Explicit instructions require the agent to separate observations from findings and maintain a deterministic planning process to avoid executing embedded instructions.
  • Capability inventory: The skill has filesystem read/write access for reports and executes a local shell script.
  • Sanitization: User requests are normalized into a structured brief before being passed to the analysis engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 06:16 PM
Security Audit — agent-trust-hub — seo