writing-shape

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, creating a surface for indirect prompt injection. \n- Ingestion points: The agent reads a user-supplied 'raw material markdown file' as its primary input in SKILL.md. \n- Boundary markers: The instructions do not include specific delimiters or directives to ignore instructions potentially embedded within the input material. \n- Capability inventory: The skill has file-reading and file-appending capabilities during its operation. \n- Sanitization: There is no explicit sanitization or filtering of the content extracted from the input pile before it is integrated into the output article.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 04:40 AM
Security Audit — agent-trust-hub — writing-shape