wiki-query

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface exists in the wiki processing workflow.
  • Ingestion points: Data is ingested from files in the 'memory/wiki/' directory using 'Read' and 'Grep' tools.
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore instructions embedded within the wiki files during synthesis.
  • Capability inventory: The skill utilizes 'Read', 'Write', 'Edit', 'Glob', and 'Grep' tools, enabling file system modifications in the 'memory/' path.
  • Sanitization: Absent. The skill does not implement validation or sanitization of content retrieved from the wiki before it is processed or written back to 'memory/wiki/' and 'memory/log.md'.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 12:19 PM
Security Audit — agent-trust-hub — wiki-query