seo-mastery
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to execute a shell command (
ls) to probe specific local directories (e.g.,~/.claude/skills/,~/.agent/skills/) to check for the presence of recommended companion skills on first activation (File: SKILL.md).\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing additional related skills from the same organization using thenpx skills addcommand (Files: README.md, SKILL.md).\n- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes potentially untrusted external content.\n - Ingestion points: The skill analyzes and optimizes external data including page titles, meta descriptions, and schema markup (File: SKILL.md).\n
- Boundary markers: Absent; the instructions do not provide delimiters or warnings to ignore embedded instructions within the processed SEO data.\n
- Capability inventory: The skill instructs the agent to perform directory listings and package installations via shell commands (File: SKILL.md).\n
- Sanitization: Absent; there are no instructions to validate, filter, or escape the metadata before processing.
Audit Metadata