skills/reason-machines/marketing-skills/r06-alirezarezvani-claude-code-tresor-seo/Gen Agent Trust Hub
r06-alirezarezvani-claude-code-tresor-seo
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to install code from an unverified GitHub repository (
LairLightningDerrick/r06-alirezarezvani-claude-code-tresor-seo) and a non-standard npm package (r06-alirezarezvani-claude-code-tresor-seo). These sources do not belong to trusted organizations or the recognized vendor infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection by processing external, untrusted data.
- Ingestion points: The skill ingests data from user-provided URLs during site audits (
/content-audit,/technical-seo), SERP analysis results, and competitor website content. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential instructions found within the crawled web content.
- Capability inventory: The skill has the capability to perform network operations, write output files (CSV, JSON, Markdown), and send notifications via Slack webhooks.
- Sanitization: The documentation does not specify any sanitization, filtering, or validation of the content retrieved from external websites before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill defines a wide array of commands that execute complex workflows, including site crawling and API interactions, which could be exploited if the underlying scripts or the data they process are compromised.
Audit Metadata