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

okf-csv

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided CSV files and incorporates their contents into generated markdown documentation, creating a surface for indirect prompt injection.\n
  • Ingestion points: The produce command (in main.go) reads CSV files from a directory specified by the user via the --dir flag.\n
  • Boundary markers: The skill does not implement specific delimiters or safety instructions to prevent the agent from interpreting data within the CSV as instructions.\n
  • Capability inventory: The skill has the ability to read from and write to the local file system and is intended for use within a CLI environment.\n
  • Sanitization: While data is sanitized for markdown table formatting using okf.SanitizeCell, raw data samples are embedded when the --sample flag is used.\n- [EXTERNAL_DOWNLOADS]: The skill instructions include downloading the connector tool from an external repository.\n
  • Evidence: SKILL.md contains the command go install github.com/xSAVIKx/okf-skills/skills/okf-csv@latest to install the tool via the Go toolchain.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:02 PM