org-agenda-api-production
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
justutility from a local dotfiles directory (~/dotfiles/org-agenda-api). - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from an external API that can influence agent behavior.
- Ingestion points: API responses from
/get-all-todosand/agenda(SKILL.md). - Boundary markers: Absent.
- Capability inventory: Shell command execution via
just(SKILL.md) and network interaction viacurl. - Sanitization: None provided for API response data.
Audit Metadata