The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local script scripts/analyze-keywords.ts using the bun runtime to perform its primary keyword density and distribution analysis. This is a functional requirement of the skill and uses standard command-line parameters for input.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external content (via URLs or file paths). This creates a potential surface for indirect prompt injection if the processed content contains malicious instructions intended to influence the agent's behavior.
Ingestion points: The <url-or-path> argument passed to scripts/analyze-keywords.ts in SKILL.md.
Boundary markers: None explicitly defined in the skill instructions to separate content from instructions.
Capability inventory: The skill utilizes local command execution (bun run) to process data.
Sanitization: No specific sanitization or filtering logic is described in the prompt instructions for the external content.
[SAFE]: All instructions and referenced scripts relate directly to the stated purpose of SEO content auditing (E-E-A-T scoring, metadata validation, and semantic analysis). No obfuscation, data exfiltration, or persistence mechanisms were detected.

seo-content