pp-semrush

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the semrush-pp-cli tool using npx from @mvanhorn/printing-press-library and go install from github.com/mvanhorn/printing-press-library. These sources are associated with the developer's official infrastructure.
  • [COMMAND_EXECUTION]: The agent uses the Bash tool to execute the semrush-pp-cli binary for processing SEO data and managing project configurations.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it ingests data from the external Semrush API.
  • Ingestion points: Output from Semrush API calls processed via semrush-pp-cli (SKILL.md).
  • Boundary markers: Uses a structured JSON response envelope with a results field to separate data from metadata (SKILL.md).
  • Capability inventory: The agent has the ability to execute shell commands via the Bash tool (SKILL.md).
  • Sanitization: No explicit mention of sanitizing or escaping content retrieved from the API before it is processed by the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 02:30 AM
Security Audit — agent-trust-hub — pp-semrush