arkweb-design-doc
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external files (analysis documents, proposals, and templates) to generate new documentation, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill reads multiple markdown files from the
{DOCS_REPO}directory, including{DOCS_REPO}/analysis/*.md,{DOCS_REPO}/docs/*.md, and{DOCS_REPO}/assets/templates/*.md.\n - Boundary markers: Absent; there are no instructions to the agent to disregard instructions or treat the ingested content strictly as data.\n
- Capability inventory: The skill performs file read and write operations but does not have network access or arbitrary command execution capabilities.\n
- Sanitization: Absent; there is no mention of sanitizing or validating the content read from external files before it is interpolated into the final output documents.
Audit Metadata