iblai-api-agent-support
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests ticket descriptions and message contents that are authored by users or agents. These fields are documented to contain HTML or Markdown, which creates a vulnerability surface where an attacker could embed malicious instructions for the agent.
- Ingestion points: Untrusted data enters the agent context via the
GETendpoints for tickets and messages described inSKILL.md. - Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent differentiate between ticket data and administrative instructions.
- Capability inventory: The skill possesses capabilities to modify ticket statuses, send replies, and delete tickets/messages across all endpoints in
SKILL.md. - Sanitization: While the documentation warns that content may be HTML or Markdown, it does not provide explicit requirements for the agent to sanitize or escape this content before processing it.
Audit Metadata