The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute Python commands during its workflow. Specifically, it runs python3 -m surge_agent.uiux search across multiple domains (landing, product, and ux) to retrieve design patterns.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection and command injection via the {product_type} variable used in shell commands.
Ingestion points: The {product_type} value is provided by the user and ingested into the search workflow in SKILL.md.
Boundary markers: None. The input is placed inside double quotes within the shell command, but this does not prevent injection via shell metacharacters like backticks or command substitution.
Capability inventory: The skill has access to the Bash tool, allowing it to execute system-level commands (SKILL.md).
Sanitization: There is no evidence of validation or sanitization for the {product_type} variable before it is passed to the shell.
[EXTERNAL_DOWNLOADS]: The skill references a vendor repository at https://github.com/tonone-ai/tonone and a platform-specific reporting tool /atlas-report for delivering HTML findings.

surge-landing