agent-data-search
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing data from external APIs and their documentation, which can be a vector for malicious instructions.
- Ingestion points: The agent reads API contracts and documentation via the
agent-data docscommand and retrieves live records (such as posts or papers) by calling discovered APIs inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted content from the system prompt or user instructions.
- Capability inventory: The skill uses the
agent-dataCLI for discovery and documentation inspection, and it provides a workflow for calling APIs and potentially transitioning to other skills for building or extending APIs based on findings. - Sanitization: There is no requirement or guidance for the agent to sanitize, validate, or escape the content retrieved from external API sources before processing it.
Audit Metadata