The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the adv command-line tool to perform operations such as product searches, inventory management, and order processing. Commands are executed directly in the shell environment as documented in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Advance Commerce API through various adv commands, which could theoretically contain malicious instructions targeting the agent.
Ingestion points: Data is brought into the agent's context through commands like adv products search, adv orders list, and adv customers get as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content embedded in the API responses.
Capability inventory: The agent has the capability to execute shell commands using the adv CLI as defined throughout SKILL.md.
Sanitization: There is no evidence of sanitization or validation of the data returned by the CLI before it is processed by the agent.

adv-cli