find-design-agency
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructs the agent to automatically scan for the
SERVICEGRAPH_TOKENin shell environment variables and local sensitive files including.envand.env.local. It explicitly directs the agent to 'use it; don't ask' if found, which bypasses user confirmation for accessing potentially sensitive configuration files. - [PROMPT_INJECTION]: The skill processes data from an external source (ServiceGraph API), which presents a surface for indirect prompt injection.
- Ingestion points: External data enters the agent context via responses from the
api.servicegraph.coAPI endpoints (/v1/search, /v1/get). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat API-returned content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill utilizes network operations via
curl,fetch, orrequeststo interact with the external API. - Sanitization: There is no evidence of sanitization or validation logic for the content retrieved from the API before it is presented to the user or processed by the agent.
Audit Metadata