plan-mtng-tools-vue
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from
./spec/README.md, which creates a vulnerability surface where instructions embedded in the specs could be executed by the agent. - Ingestion points: The skill reads
./spec/README.md. - Boundary markers: There are no defined delimiters to isolate user-provided data from agent instructions.
- Capability inventory: The skill possesses file-writing capabilities.
- Sanitization: There is no evidence of sanitization for the ingested file content.
Audit Metadata