The Agent Skills Directory

[COMMAND_EXECUTION]: The skill functions by executing a local binary or script located at ~/teneo-skill/teneo. It instructs the agent to run various bash commands to interact with the Amazon marketplace.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process external data from Amazon, which is an untrusted source that could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested through the product, search, and reviews commands described in SKILL.md.
Boundary markers: The instructions do not define clear delimiters or provide the agent with guidance to ignore instructions embedded within the scraped Amazon data.
Capability inventory: The skill possesses terminal execution capabilities via the Teneo CLI tool.
Sanitization: There is no evidence of sanitization or filtering being applied to the data retrieved from Amazon before it is processed by the agent.

amazon-teneo