arken-inspect-evidence
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch the public ARKEN catalog fromhttps://usearken.com/api/v1/deal-types. This is the official API endpoint for the service the skill is designed to interact with. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from an external API (
usearken.com) to generate negotiation checklists, creating a surface where instructions embedded in the API data could influence the agent. - Ingestion points: Data is received from the GET request to
https://usearken.com/api/v1/deal-types(SKILL.md). - Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore instructions within the fetched data.
- Capability inventory: The skill uses the fetched content to generate reasoning and checklists for the user.
- Sanitization: No specific sanitization or validation of the API response is defined before it is processed by the agent.
Audit Metadata