seo-audit
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from untrusted external websites.
- Ingestion points: Untrusted data enters the agent context through web_fetch and curl operations in SKILL.md.
- Boundary markers: The instructions do not define boundary markers or provide instructions to ignore embedded instructions for the fetched content.
- Capability inventory: The skill uses exec curl and generates reports based on external data.
- Sanitization: No sanitization or validation of the fetched content is performed.
- [COMMAND_EXECUTION]: The skill includes instructions for the agent to run shell commands using curl with variable URL inputs.
- Evidence: Shell command templates such as "exec curl -sIL " and "curl -s | grep ..." are present in SKILL.md. This pattern presents a risk if the user-provided URL is not properly sanitized before being passed to the shell.
Audit Metadata