case-study-and-proof
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data provided by the user, such as customer quotes, business metrics, and project descriptions. This creates a potential surface where malicious instructions could be embedded in the processed data to influence the agent's behavior.
- Ingestion points: The skill accepts various inputs including "The customer and what changed", metrics, and "any quote with a name and role" as defined in the SKILL.md frontmatter.
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat these inputs as untrusted content, which may increase the risk of the agent following instructions hidden within the case study data.
- Capability inventory: The skill utilizes a local script (resources/proof-check.js) for logic processing. This script only performs data scoring and does not have capabilities for network operations or file system writes.
- Sanitization: The skill lacks sanitization or validation mechanisms to filter or escape the external content before it is processed by the agent or the local script.
Audit Metadata