landing-page-design
Fail
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill directs the agent to download and execute a shell script from https://cli.inference.sh using the pattern 'curl ... | sh'. This is a critical security risk as it allows for the execution of unverified remote code on the host system without integrity checks or user review.- [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute various commands including 'infsh' and 'npx'. These tools interact with the network and local environment, presenting a risk if they are used to process untrusted data or if the tools themselves are malicious.- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content through the search assistant tool 'tavily/search-assistant'. This content is ingested into the agent's context without sanitization, creating a surface for indirect prompt injection where an attacker could influence the agent's behavior via search results.
- Ingestion points: Output from 'infsh app run tavily/search-assistant' in SKILL.md.
- Boundary markers: None identified.
- Capability inventory: Shell execution capabilities via the Bash tool and infsh CLI.
- Sanitization: No sanitization or validation of the retrieved search results is implemented.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata