wiki-sync

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process unstructured research notes, which introduces a risk where malicious instructions embedded in those notes could influence the agent's behavior during the wiki creation process.\n
  • Ingestion points: The 'Workflow' section in SKILL.md indicates the skill audits existing notes and extracts concepts from unstructured data.\n
  • Boundary markers: The instructions lack specific boundary markers or 'ignore' commands to prevent the agent from executing instructions found inside the notes being processed.\n
  • Capability inventory: The skill possesses the capability to write and update markdown files on the filesystem, as seen in the 'Create/update pages' and 'Build index' steps of the workflow.\n
  • Sanitization: There are no defined steps for sanitizing or validating content extracted from notes before it is written to the wiki files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:32 AM