The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute several local Python scripts (brand_scanner.py, citability_scorer.py, fetch_page.py, generate_pdf_report.py, llmstxt_generator.py) to perform core logic, including brand scanning and PDF report generation.\n- [EXTERNAL_DOWNLOADS]: The skill fetches HTML content and metadata from user-provided URLs using the WebFetch tool and the requests library in its Python scripts.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted content from the web for analysis. \n1. Ingestion points: The scripts fetch_page.py and citability_scorer.py fetch content from arbitrary URLs via the requests library. \n2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the fetched data. \n3. Capability inventory: The skill has the ability to execute shell commands (Bash), fetch web data (WebFetch), and write files (Write). \n4. Sanitization: Fetched HTML is parsed for text, but no specific prompt injection sanitization is performed on the content before it is provided to the agent.

geo