The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing external data that could contain adversarial instructions.
Ingestion points: The skill reads local documentation in references/api_reference.md, fetches live documentation from https://www.extruct.ai/docs, and ingests research results from company tables via GET /v1/tables/{table_id}/data.
Boundary markers: The workflow lacks explicit delimiters or instructions to ignore embedded commands within the fetched external data.
Capability inventory: The skill is capable of performing HTTP GET, POST, and DELETE requests to the Extruct API and updating local markdown files.
Sanitization: No sanitization or validation of the documentation or research results is performed before the data is used to influence the agent's workflow.
[COMMAND_EXECUTION]: The skill executes a shell command to verify the local environment configuration.
Evidence: In SKILL.md, the skill runs test -n "$EXTRUCT_API_TOKEN" to check for the presence of the required API token before initiating API interactions.

list-enrichment