calendly
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Calendly API responses, which represents a potential attack surface for indirect prompt injection if those resources contain malicious instructions.
- Ingestion points: The agent retrieves data from external Calendly endpoints using the
calendly list-events,calendly event-types, andcalendly requestcommands inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat external API data as untrusted or separate from system instructions.
- Capability inventory: The skill has the capability to perform network mutations (such as canceling events) via the
calendly requesttool, though it is instructed to ask for confirmation. - Sanitization: There is no mention of sanitizing, escaping, or validating the JSON content returned from the CLI before the agent processes it.
Audit Metadata