The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute a local script located at scripts/analyze-keywords.ts using the bun run command. This script is used to perform keyword density and semantic analysis on a user-specified URL or file path.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, which introduces a potential surface for indirect prompt injection.
Ingestion points: Untrusted data is brought into the agent context from external URLs or file paths as specified in the analysis command in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded in the analyzed content.
Capability inventory: The skill has the capability to execute shell commands via the bun runtime.
Sanitization: No sanitization, filtering, or validation of the content retrieved from external sources is described before that content is used to influence the resulting content brief.

seo-content-brief