The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands that incorporate user-supplied inputs, such as site URLs and domains (e.g., python scripts/site_crawler.py --url <site>). This pattern poses a risk of command injection if the input strings are not properly sanitized before execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to crawl external websites and analyze their content, including titles, meta descriptions, and body text. This introduces a surface for indirect prompt injection, where a malicious website could include hidden instructions intended to manipulate the agent's analysis or report output.
Ingestion points: Data retrieved from external URLs via site_crawler.py and dfs_client.py (SKILL.md).
Boundary markers: Absent; there are no specific instructions or delimiters defined to isolate or sanitize the data retrieved from external crawls.
Capability inventory: File system write operations for report generation (CRAWL-<domain>-<date>.md), directory creation, and execution of multiple analysis and rendering scripts (SKILL.md).
Sanitization: Not mentioned; the skill relies on the referenced scripts to handle and process external HTML content safely.

crawl-analyzer