wiki-ingest

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via untrusted source material.\n
  • Ingestion points: Files in the raw/ directory are read and processed (SKILL.md).\n
  • Boundary markers: The skill does not define markers to separate source content from instructions.\n
  • Capability inventory: The skill allows reading from raw/ and writing to wiki/log.md, wiki/index.md, wiki/overview.md, and wiki/synthesis.md (SKILL.md).\n
  • Sanitization: No content validation or escaping is applied to the raw data before wiki insertion.\n- [NO_CODE]: This skill consists of markdown-based instructions only and does not include any associated code or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:08 PM
Security Audit — agent-trust-hub — wiki-ingest