The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include bash commands that interpolate user-supplied input (<topic>) directly into shell execution strings (e.g., python scripts/dfs_client.py serp --keyword "<topic>"). This pattern is vulnerable to command injection if a user provides a topic containing shell metacharacters (e.g., topic; malicious_command).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data from live search engine results (People-Also-Ask questions and related keywords).
Ingestion points: Data returned by scripts/dfs_client.py from live SERP and related keyword pulls.
Boundary markers: No specific delimiters or instructions to ignore embedded instructions within the harvested questions are provided.
Capability inventory: The skill possesses the ability to execute Python scripts, write files to the local file system (using the $SEO_REPORTS_DIR path), and potentially publish reports.
Sanitization: There are no instructions provided to sanitize or validate the content retrieved from external search results before it is processed by the agent.

faq-generator