generate-mindmap
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided text, topics, or files to create structured mind maps. Maliciously crafted content could attempt to influence the agent's behavior during the analysis phase.
- Ingestion points: The skill takes input from user-provided text or files as described in the
TRIGGER WHENsection ofSKILL.md. - Boundary markers: The instructions lack explicit delimiters (e.g., XML tags or clear separators) to isolate the user's content from the agent's processing logic.
- Capability inventory: The workflow includes writing the final JSON output to the local file system at
/tmp/mindmap-outline.json. - Sanitization: There is no evidence of input validation or sanitization procedures to filter instructions embedded within the user data.
Audit Metadata