tech-seo-audit

Warn

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/tech-seo-auditor.py using a user-provided URL as a command-line argument. This pattern creates a risk of command injection if the input URL is not strictly validated or sanitized before being passed to the shell.
  • [DATA_EXFILTRATION]: The skill is configured to read sensitive brand profiles, compliance rules, and configuration files from the user's home directory (specifically ~/.claude-marketing/). Accessing files outside the skill's own package increases the surface area for unauthorized data exposure if the agent is compromised.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection as it ingests and processes content from external websites.
  • Ingestion points: The {url} parameter provided by the user is passed to the tech-seo-auditor.py script, which fetches data from remote servers.
  • Boundary markers: The instructions do not define clear boundaries or delimiters to separate external website content from the agent's internal instructions.
  • Capability inventory: The skill has the capability to execute subprocesses (python scripts/tech-seo-auditor.py) and read files from the local filesystem (~/.claude-marketing/).
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the external URLs before it is processed for the audit report.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 01:18 AM