video-resize-api
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to fetch and load external markdown documentation from
https://www.pixazo.ai/models/video-resize-api.mdto resolve parameter details and schemas. This external content is ingested into the agent's context without explicit boundary markers or sanitization, creating a surface for indirect prompt injection attacks where malicious instructions hidden in the documentation could influence agent behavior. - Ingestion points: Remote markdown documentation fetch (referenced in
SKILL.md). - Boundary markers: None specified for the fetched content.
- Capability inventory: The skill performs network requests to
gateway.pixazo.ai, writes credentials to the local file system (~/.pixazo/api-key), and executes shell commands for permission management (chmod). - Sanitization: No sanitization or validation of the fetched markdown content is described.
- [EXTERNAL_DOWNLOADS]: The skill references an external markdown file at
https://www.pixazo.ai/models/video-resize-api.mdfor extended configuration and parameters. This resource is hosted on the vendor's official domain and is intended for context enrichment. - [COMMAND_EXECUTION]: The skill provides instructions for the agent to manage API keys, including creating a local configuration file and executing
chmod 600to secure the file. It also references a command (npx skills add Pixazo-AI/skills) for installing additional vendor-owned skills.
Audit Metadata