seo-profound
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the user or agent to execute local shell scripts (install.sh) or PowerShell scripts (install.ps1) located in the extensions/profound/ directory for setup purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches citation rates and brand-mention data from the external Profound API, which constitutes untrusted input that is processed without explicit sanitization.
- Ingestion points: Data returned from the Profound API via commands like /seo profound citations and /seo profound prompts (found in SKILL.md).
- Boundary markers: None specified in the instructions to differentiate between external data and agent instructions.
- Capability inventory: The skill uses tool calls to retrieve and display brand citation information and top prompts.
- Sanitization: No sanitization or validation logic is described for the retrieved LLM citation data.
Audit Metadata