international-seo
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command (
ls) to inspect hidden directories (such as~/.claude/skills/) to identify installed companion skills and suggest additional tools if missing. - [EXTERNAL_DOWNLOADS]: The skill documentation references the installation of additional packages using
npxand provides links to resources on the vendor's official domain (absolutelyskilled.dev). - [PROMPT_INJECTION]: The skill is vulnerable to indirect injection from processed data. Evidence: 1. Ingestion points: HTML and XML sitemap content (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Local filesystem inspection via
ls. 4. Sanitization: Absent.
Audit Metadata