okf-project-knowledge-base
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes documentation standards and does not perform automated execution of code, network operations, or sensitive data access. It is primarily a workflow specification for structured markdown documentation.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes an explicit 'Publicity fence' instruction to prevent the commitment of secrets or credentials to Git history, which is a recognized security best practice.
- [EXTERNAL_DOWNLOADS]: References official documentation from well-known and trusted sources, including Google Cloud Platform's GitHub repository for the Open Knowledge Format and the IETF RFC for OAuth2 PKCE. These are established technical standards and do not involve untrusted remote code execution.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves reading data from project files (bundles), it establishes clear boundary markers using YAML frontmatter and Markdown footnote attribution. The instructions emphasize human verification for trust tiers and localized preamble rules to mitigate risks from processed content.
Audit Metadata