hiro-task-manager-cli
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by instructing the agent to ingest content from external files and standard input. \n
- Ingestion points: Commands like
tasks add,tasks update,boards add,boards update, andboards configureuse flags such as--body-file,--body-stdin,--description-file,--description-stdin,--file, and--stdinto read data from outside the prompt context. \n - Boundary markers: No instructions are provided to delimit the ingested content or warn the agent to ignore instructions within it. \n
- Capability inventory: The CLI has mutation capabilities including creation, modification, and permanent deletion (purge) of tasks, boards, and lists. \n
- Sanitization: The skill lacks instructions for validating or escaping external input before processing.
Audit Metadata