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 just utility 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-todos and /agenda (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution via just (SKILL.md) and network interaction via curl.
  • Sanitization: None provided for API response data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:28 AM