The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download the endorctl package from the npm registry as a fallback mechanism for querying findings.
[REMOTE_CODE_EXECUTION]: Downloads and executes the endorctl package from the npm registry. This is a vendor-provided tool intended for interacting with the Endor Labs platform.
[COMMAND_EXECUTION]: Executes a shell command using npx -y endorctl to query the Endor Labs API and list findings.
[PROMPT_INJECTION]: The skill processes security findings from external sources, which constitutes an indirect prompt injection surface if findings contain malicious payloads.
Ingestion points: Data retrieved via get_resource or npx endorctl in SKILL.md.
Boundary markers: Absent; no delimiters or explicit instructions to ignore embedded content are provided.
Capability inventory: The agent can execute CLI commands (npx) and read local files.
Sanitization: No explicit sanitization or validation of the findings' content is mentioned before it is processed or displayed.

endor-findings