seo-competitors

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local scripts located at ~/.claude/skills/seo/scripts/, including preflight.sh, domain_overview.py, and keyword_research.py, to perform domain analysis and credential verification.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating user-provided inputs like <domain> and <competitor> directly into shell commands.
  • Ingestion points: User input for domain targets in SKILL.md.
  • Boundary markers: No delimiters are used in the shell command templates.
  • Capability inventory: Uses the Bash tool to execute Python and Shell scripts with user-supplied arguments.
  • Sanitization: There is no evidence of input validation or sanitization before the data is passed to the shell scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 11:10 AM
Security Audit — agent-trust-hub — seo-competitors