skos-taxonomy

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill contains a hardcoded API key (panda-typesense-key) used in Typesense cURL examples for local development.
  • [COMMAND_EXECUTION]: The skill includes shell commands such as curl and kubectl port-forward intended for interacting with local development infrastructure and managing database services.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection through the processing of untrusted data. * Ingestion points: The skill ingests agent interactions, documents, and external labels to perform classification and mapping within the taxonomy. * Boundary markers: There are no explicit boundary markers or instructions to disregard embedded commands within the ingested data. * Capability inventory: The skill environment supports command-line tools like curl and kubectl to interact with external services. * Sanitization: While basic normalization (trim, slugify) is mentioned, it is insufficient to prevent instructions embedded within processed taxonomy labels from influencing agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 11:04 PM