wiki-ingest

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external content from raw/ source paths to generate wiki pages.
  • Ingestion points: Source documents found in raw/ paths (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for the read content.
  • Capability inventory: The skill has the ability to create and update multiple wiki pages using wiki_write_page (SKILL.md).
  • Sanitization: The skill relies on behavioral instructions (neutral voice, factual excerpts) rather than technical filtering. This is a characteristic of the skill's primary function and is mitigated by the structured workflow.
  • [SAFE]: The skill utilizes vendor-specific tools like wiki_read_source and wiki_write_page for legitimate project management. It includes verification steps to ensure that source pages are correctly created and that no immutable raw files are modified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:59 PM
Security Audit — agent-trust-hub — wiki-ingest