iblai-api-profile
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlcommands to interact with the ibl.ai API atapi.iblai.appfor managing user accounts and career data, including education and experience records. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
- Ingestion points: The agent reads potentially untrusted content such as user biographies, account metadata, and resume data via the API endpoints defined in
SKILL.md. - Boundary markers: There are no specific delimiters or instructions provided to ensure the agent ignores embedded instructions within the retrieved profile data.
- Capability inventory: The skill allows the agent to execute shell commands (
curl) and perform write operations to the platform API as specified inSKILL.md. - Sanitization: No content validation or sanitization is mentioned for the data fetched from the API.
Audit Metadata