validate
Warn
Audited by Snyk on Jul 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md routes runtime execution to
scripts/okf_validate.py, which reads and parses every*.mdfile in the provided/target OKF bundle directory (including YAML frontmatter and markdown bodies), so outsider-authored free text from an untrusted bundle can be ingested into the tool (as parsed strings and error/warning messages) and thus can reach the agent’s LLM context via the skill’s printed/--jsonoutputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata