The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as books, articles, and conversations for the purpose of academic verification.
Ingestion points: External research claims, study quotes, and citation metadata are provided as input to the verification workflow (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from executing instructions that might be embedded within the academic claims.
Capability inventory: The skill utilizes gbrain query for local data access, performs file writing to the concepts/ directory, and initiates network-enabled searches via the perplexity-research skill.
Sanitization: The instructions do not specify any validation, filtering, or escaping of the ingested claim content before it is used in further prompts or stored in the local knowledge base.

academic-verify