The Agent Skills Directory

[DYNAMIC_EXECUTION]: The script scripts/run_route.py dynamically modifies the Python search path (sys.path) at runtime to include directories (src) relative to the script's location for importing the geo_seo_hub module. Loading code from computed paths is a medium-risk practice that can be influenced by changes to the filesystem.- [COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to run python3 scripts/run_route.py --text "<request>". This creates a command injection surface because the user-supplied <request> is placed directly into a shell command string. A malicious user could provide input containing shell metacharacters (e.g., semicolons, backticks) to execute arbitrary code within the agent's environment.- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted user data without specific boundary protections or sanitization logic.
Ingestion points: User request text is interpolated into a shell command argument in SKILL.md.
Boundary markers: Absent; user input is embedded directly in the command line without delimiters or instructions to ignore embedded commands.
Capability inventory: The skill allows shell command execution via the bash environment and has read-only filesystem access.
Sanitization: The skill lacks explicit validation or escaping of the input string before it is passed to the execution environment.

geo