clade-model-inference
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use the
@claude-ai/sdkpackage for Node.js implementations. This is not the official Anthropic SDK (which is@anthropic-ai/sdk). Directing users or agents to install non-official packages increases the risk of supply chain attacks or using unvetted code.\n- [PROMPT_INJECTION]: The skill implements a pattern in Step 3 ofSKILL.mdwhere model output is directly parsed as JSON and used in logic. This represents a surface for indirect prompt injection if the model processes untrusted data.\n - Ingestion points: LLM output retrieved via
message.content[0].textinSKILL.md.\n - Boundary markers: None; the system prompt does not include markers to distinguish instructions from data.\n
- Capability inventory: The skill uses
JSON.parse()to process the output, which then controls subsequent logic flow.\n - Sanitization: There is no validation or sanitization of the model's output before it is parsed or used.
Audit Metadata