The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from Instagram (profiles, posts, hashtags, comments) which could theoretically contain malicious instructions.
Ingestion points: The agent accepts user-supplied arguments such as <username>, <url>, and <hashtag> which are passed to the teneo CLI tool in SKILL.md.
Boundary markers: The instructions do not specify any delimiters or safety markers to wrap the content returned from the external sources.
Capability inventory: The skill uses terminal commands (~/teneo-skill/teneo command ...) to interact with the Teneo network, as described in SKILL.md.
Sanitization: No explicit sanitization or filtering of the retrieved Instagram content is described in the prompt instructions.
[COMMAND_EXECUTION]: The skill instructs the agent to execute bash commands using a local CLI tool.
Evidence: Multiple examples of terminal commands using ~/teneo-skill/teneo are provided in SKILL.md to perform data retrieval.
[EXTERNAL_DOWNLOADS]: The skill references source code and SDKs hosted on GitHub.
Evidence: References to github.com/TeneoProtocolAI/teneo-skills and github.com/TeneoProtocolAI/teneo-agent-sdk are found in SKILL.md. These resources originate from the vendor's official GitHub organization.

instagram-agent-teneo