wiki-import

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection (Category 8) by importing and processing untrusted external data sources to populate an Obsidian vault.
  • Ingestion points: The skill reads from user-provided graph.json files and markdown files within OKF bundles, extracting fields such as titles, summaries, and page bodies.
  • Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious embedded instructions within the imported text content.
  • Capability inventory: The skill utilizes capabilities to create directories and write or merge markdown files within the defined vault path ($OBSIDIAN_VAULT_PATH).
  • Sanitization: No sanitization, escaping, or validation logic is specified for the imported text to prevent future instruction exploitation if the agent reads the reconstructed pages.
  • [SAFE]: No evidence of credential exfiltration, obfuscation, unauthorized network operations, or persistence mechanisms was found. The skill's behavior is consistent with its stated purpose as a data migration tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 12:45 AM
Security Audit — agent-trust-hub — wiki-import