acp-cart
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch external files, specifically OpenAPI documents (
openapi.cart.yaml) and JSON schemas (schema.cart.json), from a public repository on GitHub to ensure the implementation matches the current API version. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests untrusted external data which is then used to drive code generation and execution activities.
- Ingestion points: External content is retrieved via
WebFetchfrom GitHub repositories and throughWebSearchqueries targeting developer documentation. - Boundary markers: The instructions lack explicit delimiters or guidance for the agent to disregard instructions that might be embedded within the retrieved specification files or search results.
- Capability inventory: The skill has access to powerful tools including
Write,Edit, andBash, which could be misused if the agent obeys malicious instructions found in the external data. - Sanitization: There is no specified mechanism for sanitizing or validating the content of the fetched specifications before they are processed by the agent.
Audit Metadata