Skills
skills/1nfsh-s3/skills/pitch-deck-visuals/Gen Agent Trust Hub

pitch-deck-visuals

Fail

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs users to install the inference.sh CLI by executing curl -fsSL https://cli.inference.sh | sh. This pattern is a significant security risk as it downloads and executes an unverified script from a remote server with shell privileges, which could be used to compromise the host system.- [COMMAND_EXECUTION]: The skill relies on the Bash tool with infsh * permissions to execute complex commands, including running various external applications for image generation and data processing.- [EXTERNAL_DOWNLOADS]: In addition to the installation script, the skill recommends adding additional components using npx skills add, which fetches and executes code from the inference-sh repository on the npm registry.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests user-controlled data and interpolates it into HTML/CSS and Python code execution environments via the infsh app run command. Ingestion points: User-provided JSON input for the --input flag in SKILL.md. Boundary markers: None present to distinguish data from instructions. Capability inventory: Use of Bash(infsh *) to execute Python code and render HTML. Sanitization: No sanitization or validation of the input data is performed before execution.
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
Risk Level
HIGH
Analyzed
Mar 8, 2026, 02:51 AM