seo-schema
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's configuration explicitly enables the
Bashtool. While the provided instructions do not contain specific malicious shell commands, granting the agent access to a shell environment increases the potential impact of any successful manipulation or exploitation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of fetching and analyzing data from external, untrusted sources.
- Ingestion points: The skill retrieves page source code and content from user-provided URLs using the
WebFetchtool (SKILL.md). - Boundary markers: Absent. The instructions do not specify any delimiters or safety guidelines for the agent to distinguish between the skill's instructions and potentially malicious instructions embedded in the external HTML/content.
- Capability inventory: The skill allows access to powerful tools including
Bash,Write,WebFetch,Read,Grep, andGlob(SKILL.md frontmatter). - Sanitization: Absent. There are no mentions of data validation, escaping, or filtering of the content retrieved from the web before the agent processes it.
Audit Metadata