The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interacts with external API endpoints at api.apiclaw.io to fetch commerce data. It also references documentation and resources on the vendor's official website and GitHub repository.
[COMMAND_EXECUTION]: The documentation includes instructions to install an additional skill using the command clawhub install Amazon-analysis-skill, which invokes a vendor-specific CLI tool.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the processing of untrusted content (such as product reviews and listing titles) retrieved from external API responses.
Ingestion points: Data is ingested from the apiclaw.io API endpoints described in SKILL.md and references/openapi-reference.md.
Boundary markers: The instructions do not define clear delimiters or markers to help the agent distinguish between its own instructions and the data retrieved from the API.
Capability inventory: The skill facilitates network operations to retrieve external market and product data.
Sanitization: There is no mention of sanitization, filtering, or validation of the data retrieved from the external API before it is presented to or processed by the AI agent.

apiclaw