okf
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard instructional patterns for managing documentation bundles without high-risk autonomous triggers.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by processing user-provided markdown files from OKF bundles. This is an expected risk for documentation tools.
- Ingestion points: The agent reads markdown files and YAML frontmatter from user-specified directories using Read, Grep, and Glob tools (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested bundle content.
- Capability inventory: The skill uses Bash to execute local helper scripts (okf_init.py) and peer validation scripts, alongside Write/Edit tools for bundle management.
- Sanitization: No explicit content sanitization or safety-filtering of markdown bodies is performed before interpolation into the agent context.
Audit Metadata