local-seo
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's 'Companion check' instruction directs the agent to run a shell command (
ls) to inspect specific local skill directories (e.g.,~/.claude/skills/). This is used to check for the presence of recommended companion skills and suggest their installation if they are missing. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it processes untrusted user-supplied data (such as business names and addresses) to generate JSON-LD schema markup.
- Ingestion points: User-provided business information processed in the 'Common tasks' section of SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the interpolated user data.
- Capability inventory: The agent is instructed to perform shell command execution and file system access.
- Sanitization: No explicit data validation or sanitization logic is provided for the user-controlled inputs.
Audit Metadata