wiki-lint

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading the content of all markdown files within the user's wiki to detect broken links, orphans, and schema errors, which creates a surface for instructions embedded in those files to influence agent behavior.
  • Ingestion points: The skill recursively scans and reads all .md files in the vault (excluding blacklisted paths) to extract wikilinks, frontmatter fields, and descriptions (SKILL.md, Step 1 and Step 3).
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings to isolate the content of the files being scanned from the agent's command context.
  • Capability inventory: The skill possesses filesystem read access for the vault and filesystem write access to generate report files in the archive/ directory and update the log.md file (SKILL.md, Step 8 and Step 9).
  • Sanitization: No explicit sanitization or validation of the text extracted from the markdown files is described before the agent processes the content or includes it in its final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:48 PM
Security Audit — agent-trust-hub — wiki-lint