The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of a local CLI utility located at ~/teneo-skill/teneo. This tool is used to list agents, retrieve information, and execute commands against various specialized agents (e.g., Amazon, Instagram, CoinMarketCap).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process content from external, untrusted sources which creates an attack surface for indirect prompt injection.
Ingestion points: The skill ingests data from external platforms including Amazon product pages, Google Maps business details, Instagram profiles, TikTok video metadata, and LinkedIn profiles via the teneo command interface.
Boundary markers: No specific delimiters or boundary markers are present in the skill instructions to separate untrusted agent output from system instructions.
Capability inventory: The skill has the capability to execute shell commands through the ~/teneo-skill/teneo binary.
Sanitization: There is no evidence of sanitization, filtering, or validation of the data returned from external agents before it is processed by the AI agent.

teneo-agents