seo-content-audit
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions generate shell commands by interpolating user-provided strings such as
[domain],[client], and[competitor]into command lines (e.g.,python3 skills/site-content-catalog/scripts/catalog_content.py --domain "[domain]"). If these inputs are not properly sanitized and contain shell metacharacters like semicolons or backticks, they could lead to arbitrary command execution on the host system. - [PROMPT_INJECTION]: The skill ingests and processes content from external websites (via WebFetch and cataloging scripts) to perform brand voice extraction and content analysis. This untrusted data could contain instructions meant to manipulate the agent's behavior or poison the generated audit report.
- Ingestion points: External website content from target and competitor domains; local client context files (e.g.,
clients/<client>/context.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as data rather than instructions.
- Capability inventory: The skill executes shell scripts and performs file system read/write operations within the
clients/directory. - Sanitization: There is no mention of sanitizing web content or validating input paths before they are used in commands or logic.
Audit Metadata