knowledge-wiki
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it ingests untrusted data to create and update wiki pages.
- Ingestion points: Untrusted data enters the agent context through articles, documents, and conversation logs via the 'Ingest' and 'Synthesize' operations in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded prompts within the external source material being processed.
- Capability inventory: The agent uses tools to read files, search memory, and write or update markdown files within the
knowledge/directory. - Sanitization: No logic for sanitizing or validating input content is defined before the information is integrated into the persistent knowledge base.
Audit Metadata