org-agenda-api
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of a markdown documentation file and does not include any bundled scripts or executable code.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external API and allows the agent to perform sensitive operations based on that data.
- Ingestion points: Agenda entries and TODO items are retrieved via the
/agendaand/get-all-todosendpoints in SKILL.md. - Boundary markers: No boundary markers or instructions to ignore embedded commands are specified in the documentation.
- Capability inventory: The skill exposes endpoints to delete entries (
POST /delete), update task properties (POST /update), and mark tasks as complete (POST /complete) in SKILL.md. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from the API before it is processed by the agent.
Audit Metadata