okf-wiki-lint
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/validate_governance.pyto perform structural validation of the wiki. The script is implemented using only the Python standard library and performs read-only operations on the targeted directory. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown content from the user's wiki, creating a surface where malicious instructions embedded in wiki files could attempt to influence the agent's audit summary or qualitative judgment.
- Ingestion points: The
scripts/validate_governance.pyscript (called bySKILL.md) reads and parses all Markdown files within the user-specified wiki directory to extract frontmatter and link structures. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the wiki content being audited.
- Capability inventory: The skill has the capability to write audit results to
wiki/log.mdbased on the agent's findings (SKILL.md). - Sanitization: While the script validates structural compliance (e.g., date formats, taxonomy types), it does not sanitize or filter content that is passed to the agent for qualitative "judgment-required" checks like topic extraction or contradiction marking.
Audit Metadata