screenshot-local
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
shot-scrapertool and its required Chromium browser engine. These components are sourced from well-known and established registries. - [COMMAND_EXECUTION]: The skill operates via the
shot-scraperCLI and allows for the execution of shell commands to manage local server processes through theserverconfiguration key inshots.yml(e.g., inSKILL.mdandreference/TEMPLATES.md). - [DYNAMIC_EXECUTION]: The skill supports executing JavaScript within the browser context via the
javascriptflag and YAML key to interact with web page elements before capturing images, as described inSKILL.mdandreference/COMMAND-REFERENCE.md. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external content that could influence agent behavior.
- Ingestion points: Target URLs provided by the user and local project files (e.g., router configurations, navigation files, and page source files as suggested in
SKILL.md) that the agent parses to discover application routes. - Boundary markers: None identified. There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded in the ingested data.
- Capability inventory: Execution of CLI tools (all scripts), arbitrary shell command execution for background processes (
SKILL.md), JavaScript execution in the browser (SKILL.md,reference/COMMAND-REFERENCE.md), and the ability to save or load authentication session files (reference/COMMAND-REFERENCE.md). - Sanitization: None identified.
Audit Metadata