zmm-title
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied drafts and topics, which acts as a surface for potential indirect prompt injection.
- Ingestion points: User input provided as content drafts or topics in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore instructions within the ingested content are present.
- Capability inventory: The agent has the capability to read local reference files and write memory to the
{vault}directory. - Sanitization: No specific sanitization or filtering of the user-provided content is defined.
- [SAFE]: The skill's file access is limited to reading local documentation and writing to a designated memory path within the user's vault, which is a standard operational pattern for AI agents.
- [SAFE]: The reference to a Python script (
scripts/title_struct.py) is documentation for user-side data analysis and does not involve the agent autonomously downloading or executing remote code.
Audit Metadata