skills/xsavikx/okf-skills/okf-mongodb/Gen Agent Trust Hub

okf-mongodb

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions provide a command to install the connector binary directly from the author's GitHub repository using go install github.com/xSAVIKx/okf-skills/skills/okf-mongodb@latest.
  • [COMMAND_EXECUTION]: The connector is implemented as a CLI tool that executes subcommands (produce, ingest, schema) to sample database documents and write Markdown files to the local file system.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing data from external MongoDB collections to generate Markdown content.
  • Ingestion points: Untrusted data is ingested in main.go through the sampleCollection function, which fetches raw documents from the database.
  • Boundary markers: The generated Markdown uses standard headers and tables but does not include explicit delimiters or instructions to ignore embedded content within the inferred fields.
  • Capability inventory: The skill possesses network capabilities to connect to MongoDB and file-write capabilities via okf.WriteConceptDoc and os.MkdirAll in main.go.
  • Sanitization: The implementation in mongodb.go uses okf.SanitizeCell to escape field names and types when rendering the schema table, reducing the risk of Markdown structural manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 08:04 AM
Security Audit — agent-trust-hub — okf-mongodb