intercom-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides implementation patterns that process data from external sources (Intercom API and webhooks), which constitutes an indirect prompt injection surface. \n
- Ingestion points: The webhook handler in
references/implementation.mdprocessesreq.bodydirectly from external Intercom notifications. \n - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in the implementation examples or instructions. \n
- Capability inventory: The skill utilizes
ReadandGreptools to audit the codebase. The execution environment typically allows file system modification and shell command execution. \n - Sanitization: The implementation snippets do not include data validation, escaping, or sanitization for the incoming payloads.
Audit Metadata